Round 7 (516dffa..45aa9e1, WARN: 12 MAJOR, 0 BLOCKER) and the fence defect
found while writing its review.md. Each fix began with a test that failed on
0f400d3 (v6.3.0); suite 2208 (2206/0/2), 14 tests more.
- Tests-only (operator 2026-10-11): the plan's Files: alone decides, and the
text says so (red-proof, trekexecute Sub-step B, step-implementer,
HANDOVER-CONTRACTS). red-proof no longer reads the step's diff, so a change
already in the tree when the step began no longer counts against it, and a
plan placed outside .claude/ reads the same. The round-6 test that had the
diff overrule the plan is rewritten to the new rule.
- The Files: reader keeps a plain file beside a backticked path
(", Dockerfile", "the CLI entry src/cli.mjs", "and Makefile"). Measured on
the 520 Files: fields in 182 plans: no field reads differently.
- Red proof reports a command its timeout killed as killed after the timeout,
not "could not start"; the release check tells a timeout from output past
its buffer and from another signal. One reading of a stop
(criteria-runner stoppedBy) for red proof, the criteria runner and the
release check.
- A trailing `# comment` is dropped in a backticked check too, and in a
command passed as written, so the words screened are the words run.
- The release check reads a relative --review in --repo.
- The 15-minute timeout is defined once (criteria-runner.mjs).
- The findings check reads each cited file once per validation.
- One isMain helper (lib/util/is-main.mjs) for every CLI: the 31 copies of
the realpath guard and the 20 modules still on the file:// guard, which
exited 0 having done nothing under a symlink or a path with a space.
- The Bash guard writes its no-one-to-ask refusal once, on a direct condition.
- The findings check ends a ```json block only at a fence on its own line, so
three backticks inside a JSON string no longer end it (also in 6.2.0).
- Brief-conformance notes: a test for test-lock green on exit 127 (it
passed at once; it fails when 127 is read as could-not-run); the prose now
names the git revision `@~1` as the one leading-@ exception.
Not changed: the example plan's steps 1-2 keep their tests-only warning
(operator decision 2026-10-09; the r5 test records it). Brief note 4 (a
Regression: whose runner is not installed goes to the fix rounds) is a
routing question for the operator.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Version 6.3.0 in plugin.json, package.json, package-lock.json and the
README badge; the 6.3.0 CHANGELOG section with its Doors list and the
Known issues for 6.3.1 (release review round 7: WARN, 0 BLOCKER, 12 MAJOR;
the operator chose to release with it on 2026-10-11).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Round 6 (v6.2.0..c3641ff, WARN: 11 MAJOR, 3 MINOR; 0 BLOCKER). The round-5
fixes hold (code-correctness-reviewer); three of the new MAJOR were side
effects of running checks with no shell. Each fixed behind a test that
failed first on c3641ff.
- git checks stay in the repo too: no path that climbs out with .., starts
at / or reads <rev>:../x, and no --no-index (both reviewers).
- A trailing `# comment` on a shell-fence line is dropped: with no shell,
its words made an honest check NOT RUN, among them the first check of the
shipped example plan.
- A glob reaches `node --test` only on Node 21 and later, which expands it
itself; on an older Node it is refused with that reason (engines >=18).
- With no shell, exit 126/127 is the test program's own: red proof reads it
as a red (the control run still tells an environment fault apart), the
done line and the test lock as a failure.
- A runner that could not start (not installed) is NOT RUN in the criteria
runner and not-run (exit 2) in regression-check, as red-proof and
done-line already said; never a red suite.
- Tests-only: a backticked `Makefile` alone in its entry is a path, and red
proof confirms the plan's tests-only reading against the step's own diff
(the altitude finding: the diff is a fact, the Files: prose is not).
- release-check stops a suite that never ends (15 minutes) and reads it as
not measured (exit 2).
- The two lines this release added to pre-bash-executor.mjs are ASCII.
- MINOR: git and the other runners share one plain-word pattern.
Not in this round: MINOR f00a2eb8 (shared norm/ticked-path and isMain
helpers) and MINOR on plan-review-dedup's repeated tokenizing.
Suite 2194 (2192/0/2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Round 5 (v6.2.0..d37e538, WARN: 11 MAJOR, 2 MINOR). The patching did not
converge (the same two places every round), so the operator chose a
structural fix on 2026-10-11. Each change behind a test that failed first.
- A check runs with no shell. criteria-runner's runCommand starts the runner
with the very words the screen checked (spawnSync(words[0], words.slice(1)),
without NODE_TEST_CONTEXT); Phase 7 criteria, Regression: (its exec copy is
gone, MINOR 0e98d5c7), proof of red, the done line and the test lock all
run through it. No quote, glob, tilde or variable can rewrite a checked
word any more. The screen stays and says why: a word that means something
else in a shell (quote, backslash, $, brace, leading ~) is refused; a glob
reaches only node --test, which expands its own patterns (sh read
`tests/.?/` as `tests/../`); no path climbs out with .. or starts at /;
a word starting with @ is refused (pytest reads @file as more arguments).
- The K6 plan-file sweep has v6.2.0's own Files: reader again (516dffa):
backticked paths, and plain words only in a field without them. The
shared reader from round 3 planned directories a description named and
dropped paths v6.2.0 planned. fieldPaths stays for the tests-only check,
with a path test on spans (`parse()`, `p.parse()` are no paths), plain
descriptions ignored when the field has backticked paths, dotfiles,
backslash paths and glued spans read.
- Skill frontmatter reads a value as YAML does: trailing space is nothing,
and a comment ends a plain value, a flow list or a block indicator
(`model: opus # pinned`). A comment that cuts a plain description, or is
the whole value, is still a hazard.
- release-check reads the diff with --no-renames: a test moved into an
allowed place after the review shows as removed.
- The example plan's step 2 heading no longer says "must FAIL initially";
steps 1-2 keep the tests-only warning (operator 2026-10-09, 73262b6).
Open: MINOR c1fef1ad (one shared isMain helper) is not in this round.
Measured: 0 of 463 Files: fields with backticked paths (520 fields in 182
plans across the marketplace repos) carry another path-like word.
Suite 2185 (2183/0/2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The nine MAJOR findings of round 4 (WARN): the Files: reader keeps every
path the field names and only those (three were regressions from round 3),
quoted frontmatter values with a comment, no tilde word and nothing after
`make test` in the criteria runner, and release-check's sha and badge line.
Suite 2175 (2173/0/2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Round 4 (v6.2.0..41ea8fc, WARN: 9 MAJOR, 3 MINOR); the nine MAJOR fixed,
each behind a test that failed first (operator 2026-10-10). Three were
regressions from round 3's shared Files: reader.
- fieldPaths keeps a backticked path with punctuation after it and one
inside a note, a directory (docs/) and a glob (src/*.mjs) in plain text,
and app/(auth)/x.ts whole; a bare word counts only alone and capitalised
(Makefile), so "format" or "v6.3.0" in a description is no path. The K6
sweep plans what v6.2.0 planned for `a.mjs`: and `b.mjs`.
- skill frontmatter: a quoted value may carry a YAML comment after it.
- criteria runner: no word with a leading ~ (sh expands it), and nothing
after `make test` (another target would run).
- release-check: scope_sha_end must be a commit sha (a ref name passed
coverage whatever was reviewed), and README lines changed after the review
may differ only in the badge's version. The round-3 leading-zero example
is 7 characters now, the shortest sha accepted.
The three MINOR (one word screen for git, the exec copy in regression-check,
a shared isMain helper) are not in this round.
Suite 2175 (2173/0/2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Every allowlisted runner now takes only plain words and options that only
read (round 3's BLOCKER: rounds 1-2 closed the write-a-file class for git
only), plus the eight MAJOR and two MINOR findings: refused restores in
/trekexecute, stepTestsOnly and one Files: reader, --steps-from Verify on
1.8, skill frontmatter, routing, and release-check's sha and artifacts.
Suite 2170 (2168/0/2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Round 3 (v6.2.0..96cb977, BLOCK: 1 BLOCKER, 8 MAJOR, 2 MINOR), each fixed
behind a test that failed first.
- Every allowlisted runner, not only git, takes plain words and a short list
of options that only read: an option that writes a file or loads code
(--test-reporter-destination, --outputFile, --junitxml, --basetemp,
--import, --config, -p, -o, -exec, a reporter path) is on no list; after
`npm test --` only paths follow; `make test` takes no VAR=value. A built-in
node test reporter (tap, spec, dot, junit, lcov) stays allowed.
- /trekexecute: a restore the guard refuses (destructive git, in the mode
that shows no prompts) or the operator declines is never recorded as
reverted: simplify = "revert-refused" and the run stops before review; a
refused step revert is reported with its paths.
- stepTestsOnly: a fixture document under tests/ is a test file, "e.g." is
not a path, ./ is dropped; the plan-file sweep reads Files: with the same
reader (fieldPaths); the validator hands its parsed fields over.
- plan-validator --steps-from asks for Verify: on a 1.8 plan too.
- skill frontmatter: a value starting with # is a hazard; a quote after an
escaped backslash closes the value. Routing reads kind tags with hasOwn.
- release-check reads scope_sha_end as written (an all-digit sha keeps its
leading zero), and Voyage's own artifacts under .claude/projects/ and
.claude/voyage/ committed after the review do not count as unreviewed.
Suite 2170 (2168/0/2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The git runner's --output refusal now holds against quoting, plus the
round-2 findings in fieldPaths, --steps-from, regression-check,
release-check and skill routing. The review-step loop's limit is stated
plainly (operator 2026-10-10: runnable template steps are a later order).
Suite 2160 (2158/0/2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Round 2 (v6.2.0..0d044f6, BLOCK: 2 BLOCKER, 11 MAJOR, 1 MINOR), each fixed
behind a test that failed first.
- The git runner checks only words /bin/sh passes through unchanged (no
quote, backslash, $, glob or brace) and refuses --output and its
abbreviations: round 1's --output refusal was bypassed by quoting.
- fieldPaths: backticked paths are kept as written, parentheses and all; in
plain text every path-like word counts, and a parenthesised note does not.
- plan-validator --steps-from reads the plan's ## Verification for an
appended End-to-end step, and warns instead of failing under --soft.
- regression-check prints progress_status, the value progress.json takes;
/trekexecute copies it.
- release-check: a plugin in a subdirectory is checked in its own directory,
the suite is not run when a cheaper check already makes the answer exit 2,
and a bad argument or a crash is exit 2.
- Skill routing looks a skill up among skills only, and builds the corpus
vectors once.
- /trekexecute Phase 7.2 says plainly that remediation steps in the review
template's own form stop with a re-plan; making them runnable is a later
order (operator 2026-10-10).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Release review of v6.2.0..f669b87 (BLOCK). The BLOCKER was the review brief's
wording of a non-goal (operator 2026-10-10: order 6's review loop is in 6.3.0);
the hole behind it is closed (plan-validator --steps-from). The 12 MAJOR and 1
MINOR findings, and git --output in the criteria runner, are fixed. Suite 2148
(2146/0/2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The review of v6.2.0..f669b87 (BLOCK: 1 BLOCKER, 12 MAJOR, 1 MINOR), each
fixed behind a test that failed first, or, for the two missing tests, a test
shown to fail on a stub of the branch it covers.
- Review steps appended by /trekexecute Phase 7.2 are held to the step rules
on any plan version: plan-validator --steps-from <N> (on a plan below 1.8 a
template review step validated and was executed).
- The guard refuses where no one can be asked also when its rules will not
load; the wave merge path names that refusal instead of MERGE_REFUSED.
Tests for the classifier-error refusal and post-approval-log's own check.
- release-check: the version files may change only in their version after
the review (JSON compared without it), README diff lines are read inside
hunks only, an unreadable diff is exit 2, and npm test runs without
NODE_TEST_CONTEXT.
- What counts as a step of only tests: a note in parentheses is not a path,
and a data file under specs/ is not a test. End-to-end: rides on the last
step that builds behaviour (validator hint, trekplan, template).
- A removed line is cited as <rev>:<path>:<line> (findings-schema hint,
trekreview re-ask).
- skill-lint counts a trailing newline as no line; regression-check takes
commandEnv from lib/util/command-env.mjs; CLAUDE.md names four mode-read
exemptions.
- /security-review, older than v6.2.0: the criteria runner refuses git
--output, which writes a file.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A step of only tests can never be proven red: the plan validator warns
(PLAN_STEP_TESTS_ONLY), trekplan, the template and plan-critic say the
test belongs in the step that builds the behaviour, and the executor sends
such a step straight up to the plan. Also: timing tests tolerate one slow
run of three, the example plan uses the K11 words, trekreview knows
FINDING_PROSE_LINE_OUT_OF_RANGE and checks the whole reviewer text, the
criteria runner drops NODE_TEST_CONTEXT, and the resolver text says when
effort is absent. Branch suite 2128 (2126/0/2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Operator 2026-10-09: step 6 of examples/01-add-verbose-flag only added a
test for behaviour step 5 delivered - the pattern PLAN_STEP_TESTS_ONLY
warns on. It now lands in step 5 (Verify: the new test, red before the
wiring; Regression: the stability harness), the help-text step becomes
step 6, and progress.json follows (6 steps). Steps 1-2 (golden capture and
stability harness, tests of today's behaviour that cannot be red) keep
the warning; a step type for them is a wave 3 question.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
1. A step of only tests can never be proven red. One reading,
stepTestsOnly (lib/parsers/plan-schema.mjs, test paths from the new
lib/util/test-path.mjs): the plan validator warns PLAN_STEP_TESTS_ONLY,
red-proof --plan/--step adds tests_only to a not-red-at-base, and
/trekexecute and the step helper send such a step straight up to the
plan instead of into fix rounds that cannot succeed. /trekplan, the plan
template and plan-critic (dimension 8, still 12) say the test belongs in
the step that builds the behaviour.
2. Timing tests under load: the hook helper's kill limit is 30 s and per
call overridable; SC #14 passes on the fastest of up to three runs
against the same 800 ms limit (tests/helpers/timing.mjs).
3. The example plan's On failure lines open with a K11 word.
4. /trekreview saves the reviewer's whole answer for the findings check and
names FINDING_PROSE_LINE_OUT_OF_RANGE (error: re-ask; warning: report).
5. The criteria runner's commands run without NODE_TEST_CONTEXT
(commandEnv, moved to lib/util/command-env.mjs).
6. The resolver returns effort only when the brief's phase signal sets one;
the four commands said it always did.
Also: the K2 hook tests used fixed session ids in a per-user temp dir, so
two suites running at once took each other's approval records; the ids are
now unique per run.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Order 6 of wave 2: /trekexecute checks the approved plan (K2), runs the
step check (K9) and the step's Regression: (K10) at step end, the
architecture rules (K5) and plan-file sweep (K6) after the last step,
reviews by itself in the closing run (K7 lock on the main merge), and
the guard refuses every asked-about call where no one can be asked.
Branch suite 2102 (2100/0/2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Union lines resolved: CLAUDE.md command table keeps main's /trekresearch
and /trekplan rows and this branch's /trekexecute row. README's
architecture block now counts the three skills main ships (it said 2
after 7b added researching-sources).
Contracts run against the real ones on the merged tree: K10/K11 (plan
validator refuses a piped Regression:, warns on an unknown On failure:;
regression-check passes/fails/absent/unrunnable), S2 (skills/test-first
and skills/debugging exist, voyage:<name> form as 7a chose), K7 (real
review_version 1.1 WARN -> 0, a BLOCK copy -> 1, a 1.0 review with no
verdict -> 2). npm test: 2102 / 2100 pass / 0 fail / 2 skipped.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Order 8 of wave 2: scripts/release-check.mjs (tree, suite, review
verdict, review coverage, door type; 0 ready / 1 not ready / 2 could not
run) and docs/release-runbook.md with both rollback paths drilled in a
sandbox. Branch suite 2085 (2083/0/2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
No conflicts. npm test on the merged tree: 2085 tests, 2083 pass, 0 fail,
2 skipped (main 2055 + this branch's 30). K2 and K7 tests green against
the real modules; the verdict gate and approval log CLIs run end to end.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Order 7b of wave 2: the researching-sources skill, preloaded by the five
web agents and named by /trekresearch; two contradicting agent sentences
fixed and the confidence scale aligned. Branch suite 2055 (2053/0/2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
In the permission mode that shows no prompts, pre-bash-executor refused only a
merge into main and a push. A tag, a package publish and destructive git still
went through unattended, which is what the approval guard exists to stop. Now
every call it would ask about, and a command it could not read, is refused
there with the way forward (operator decision 2026-10-09). No new exemption:
the mode is still read in one place.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Conflict: CLAUDE.md command table. Kept both sides: this branch's
/trekresearch row (the external agents preload researching-sources) and
main's /trekplan row (open minors listed for the operator).
researching-sources adapted to contract S1, now that 7a's form check and
routing test run over it:
- SKILL.md takes the fixed headings (Overview, When to use, Process, Red
flags, Enforced by, Credits); the five rules and the confidence scale move
under Process unchanged; Red flags lists the thoughts the baseline runs
showed; "text only" becomes "prose only" as the form check reads it.
- The description adds "official" documentation and "looking up online what
an error message means or what causes it": the error-lookup case ranked
#3 behind debugging. That prompt also said "our tests fail", which is
debugging's job; it now asks only what the error means and where that is
documented. No threshold changed.
- Eval cases carry the routing tags (skill-trigger / skill-no-trigger /
skill-effect, skill=, owner= task-finder and trekplan, from=), 7a's
Skill grader pattern, arm: both on the no-trigger graders, and the
judge-model line on the effect case.
- The `## Skills` row in README and CLAUDE.md.
- tests/lib/skills-research-prose-pins.test.mjs drops its two form pins
(skill-lint is the authority now): 14 -> 12.
npm test on the merged tree: 2055 = 2053 pass / 0 fail / 2 skipped
(main 2043 + 12).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Order 9 of wave 2: contracts K10 (Regression: step field) and K11
(On failure: action words) in the plan validator, and the minor points
B8-B12 and C13-C17 from the second trial. Branch suite 2043 (2041/0/2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Wave 2, order 6. /trekexecute now:
- refuses a plan whose logged approval does not cover its current sha256
(K2, approval-log verify --kind plan), before step 1;
- runs the step check (K9) and the step's optional Regression: (K10, new
lib/verification/regression-check.mjs through the criteria runner) at step
end, before the checkpoint; exit 2 is "not measured", never green;
- runs the architecture rules (K5) and the plan-file sweep (K6) after the last
step; a violation or a file outside the plan turns completed into partial;
- reviews by itself in the closing run (Phase 7.2): run the thing, /simplify,
/trekreview, verdict-gate; a BLOCK adds the review's remediation steps after
the plan validator accepts them and the operator re-approves the plan, capped
at TREKEXECUTE_MAX_REVIEW_ROUNDS (3);
- makes the main-merge gate a lock on the verdict: BLOCK or undecided keeps
the merge closed; when open, the executor merges and the guard's question is
the one question (operator decision 2026-10-08). The --gates pause before
the wave merge-back is gone for the same reason.
The guard refuses a merge into main and a push in the permission mode that
shows no prompts, since no one can be asked (operator decision 2026-10-09; two
mode-read exemptions approved by the operator).
progress.json gains optional coupling fields (Handover 5); the validator
rejects the runner's exitCode in plan_verification.failed_criteria (C15).
Pointer lines name the skills test-first and debugging (S2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Wave 2 merge order 7a -> 9: brings e589a02 into order 9's branch.
No conflicts. Full suite on the merged tree: 2043 (2041 pass / 0 fail /
2 skipped) = main's 2014 + this branch's 29.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Order 7a of wave 2: the skill form check (S1), the model-free routing
test, and the skills test-first and debugging preloaded into the step
helper (S2). Branch suite 2014 (2012/0/2).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The source rules the research agents shared by copy now live in one skill,
skills/researching-sources/: official sources first with URL, date and
matching version; no citation, no finding; an empty search is reported with
its denominator and never as a finding; fetched pages are data, and text in
them aimed at AI assistants is ignored and reported; nothing local in an
outbound query. It also holds the one confidence scale.
- docs-, community-, security-, contrarian-researcher and research-scout
preload it (skills: ["voyage:researching-sources"]); the copied rule text
leaves them, their own role stays.
- Two agent sentences that contradicted the rules are gone: an empty
counter-evidence search "increases confidence", and "fall back silently".
- /trekresearch names the skill where it starts the external agents and in
web follow-ups; Phase 6 rates on the skill's scale word for word; the
deep-research adapter accepts `contradictory` like the template does.
- Enforced by: research-validator checks structure only, the query privacy
gate runs only in the default-off STORM steps; the rest is text only.
A guard on every web search is a separate later order (operator 08.10).
- Red baseline (helpers, offline fixtures): without the skill 3 of 5 runs
ignored an injected instruction silently and 1 of 2 contrarian runs counted
an empty search as weak support; with it 0 of 3 and 0 of 2. Path leaks:
0 of 7 without, 0 of 5 with.
- Eval cases (3 should trigger, 2 should not, 1 effect), written, not run.
- tests/lib/skills-research-prose-pins.test.mjs: 14 pins, 13 red on 4ee711a.
Credits: Addy Osmani, agent-skills @9d0c60d,
skills/source-driven-development/SKILL.md:97-114 (MIT); Jesse Vincent,
obra/superpowers @8ca22db, skills/diagnosing-superpowers/ (MIT). Ideas only.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The minor points (B8-B12, C13, C14, C16, C17) of the second voyage-lekerepo
trial (2026-10-08), each verified against the code and started with a test
that failed first.
- K10: optional step field `Regression:` - one command the criteria runner
allows, unpiped; plan-validator refuses one that can never run
(PLAN_STEP_REGRESSION_NOT_RUNNABLE). Any plan_version, no bump.
- K11: `On failure:` opens with revert | retry | skip | escalate, or the
validator warns (PLAN_STEP_ON_FAILURE_UNKNOWN); onFailureAction in
plan-schema.
- B8 (operator decision 2026-10-08): minors open after the last critic round
are listed numbered in the Phase 10 summary; the ones the operator picks are
fixed and get one more round (--extra-round when the 3 are spent).
- B11: plan-review dedup merges two reviewers' findings on the same file:line
with the same content (trial pair: Jaccard 0.44, overlap 0.83); the Jaccard
threshold for every other pair is unchanged.
- B12: /trekbrief Step 4c says the reviewer runs in the background and is
waited for, not "foreground, blocking".
- C13: the Phase 4 size count includes .mjs, .cjs, .mts, .cts.
- C14: --evidence shows the first output line on PASS rows.
- C16: findings-schema checks path:line citations in finding prose (error) and
in the prose around the block (warning) against the file.
- C17: git-historian gets the brief, never proposes changing a frozen file,
and names the remote from `git remote -v`.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The workshop (ordre 7a, contracts S1 and S2): a form check
(lib/skills/skill-lint.mjs) that follows Claude Code's own skill fields,
and a model-free routing test (lib/skills/routing.mjs) over every skill,
the 7 commands and the 21 spawnable agents, reading the eval cases
themselves (evals/skill-*, 3 fire / 2 quiet / 1 effect, tagged with the
event they came from). Thresholds pinned, never lowered.
The two skills were written against failures measured first in helpers
without them: red only as an import crash, the whole suite run from a
hand-made file list instead of the repo's own command, and an
unreproduced fix shipped under authority pressure. step-implementer
preloads both through its skills: line; no tool list change.
Credits: addyosmani/agent-skills @9d0c60d, obra/superpowers @8ca22db,
mattpocock/skills @c55ee46 (MIT), Anthropic skill-creator (Apache-2.0).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
P13 (wave 2, order 8). docs/release-runbook.md has three parts: before the
release, the release, and the rollback. The rollback was drilled first, in a
sandbox with local bare repos as the remotes: a release 6.2.0 -> 6.2.1, then
path A (git revert, catalog ref back to v6.2.0) and path B (a forward patch
6.2.2 that carries the revert), with the catalog's check-versions green after
each. Nothing reached a real remote; the real catalog was byte-identical
before and after.
Measured: release-plugin.mjs refuses a ref backwards while plugin.json still
says the newer version, and accepts it once the release commit is reverted.
scripts/release-check.mjs decides before a release: clean tree, npm test
green at HEAD, review verdict not BLOCK (K7) and covering HEAD, and a door
type per delivery (### Doors in the CHANGELOG section). 0 ready, 1 not
ready, 2 could not run (never green). A ready run prints the K2 command that
logs the operator's yes.
tests/lib/release-prose-pins.test.mjs holds every command in the rollback
part to the commands the drill ran (tests/fixtures/release-drill/).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Wave 1 (five orders, merged 2026-10-06), the fixes from the two end-to-end
trials in the test repo, and the defects an independent reader found in
them. Plan 1.7, brief 2.0-2.2 and review 1.0 files stay valid; the new
fields are optional.
Suite 1972 (1970 pass, 0 fail, 2 skipped).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- The pre-compact hook read only a checkpoint that started with `git commit`,
so every plan in the new `git add … && git commit` form rebuilt nothing, and
an empty match also skipped the session-state refresh. It now finds the
commit anywhere in the span and always refreshes; first test for the hook.
- A sub-bullet that carries its own command stays a criterion (folding it
left the command unrun); the shallowest bullet sets the base indent.
- Only a MINOR/SUGGESTION /code-review finding outside the range is released
from forbidding ALLOW: a MAJOR one may be a break cited at an unchanged
caller.
- `reuse` is an improvement category; the session-spec template stages too;
a negated bash 3.2 constraint, an env prefix and `bash -c` are handled.
- Stale comment, Declined-to-Judge wording and rule-key counts brought in line.
Tests fail on 7c11c2a first (9 of 24).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
voyage-lekerepo trial 2 (2026-10-08), report section A; the operator decided
they are fixed before the next release:
- A1: a /code-review finding whose category is simplification, efficiency,
style or readability enters as CODE_REVIEW_IMPROVEMENT (MINOR), not MAJOR.
- A2: recommended_action is the engine's own fix when transcribed, otherwise
a test-first step; never the failure scenario dressed as a remedy.
- A3: a /code-review finding outside the exact range it was given is declined
and listed, but no longer holds ALLOW back; /security-review's still does.
- A4: the manifest must_contain recipe uses grep -E -e ... -- so a pattern
like --sep is not read as an option.
- A5: indented sub-points belong to their criterion (counted), and a
criterion with sub-points and no command warns BRIEF_SC_SUBPOINTS.
- A6: a brief requiring bash 3.2 whose criterion runs plain bash warns
BRIEF_SC_BASH_NOT_PINNED; /trekbrief proposes /bin/bash.
- A7: the plan template's and /trekplan's checkpoints stage the step's files.
Tests fail on 5f9faee first (tests/lib/trial2-fixes.test.mjs, 11 of 14).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The skills reading (2026-10-06) found two defects the operator decided to fix
once wave 1 was merged:
- the brief template's Success Criteria examples used a pipe and npx, which
the criteria runner refuses (and the brief validator now warns on);
- trekcontinue and trekexecute called lib/ scripts relative to the working
directory, which is the user's repo, not the plugin.
Tests fail on the old text first (tests/lib/reading-defects.test.mjs).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Independent read-only review of c56f852..2d29966 (2026-10-08), each defect
reproduced by the reviewer; each new test fails on that code.
- test-lock green ran ANY allowlisted command: `green --cmd "git status"`
marked a red step green and the stop guard let it stop. The lock now
stores the step's test command (`lock --cmd`); `green` runs only that
one (a different --cmd, or a lock without one, exits 2). trekexecute D1
calls `green` with no command, which also removes the quoting hazard.
- plan-gate --accept-open worked at round 1 and passed the gate; it now
refuses while rounds are left.
- findings-schema --repo-root swallowed a following flag, or took a root
that does not exist, and silently skipped the line check: exit 2.
- brief-review-stamp hashed only the body, so a changed `framing` or
`research_topics` stayed "current"; it now covers the reviewed
frontmatter too (only the post-review stamps are left out).
- red-proof red_kind read an assertion message naming SyntaxError as a
load error; the signatures are now specific.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
voyage-lekerepo trial (2026-10-06) point 6, operator decision 2026-10-08
(«samme skala, og du spør»): the critics rated a non-discriminating test
minor in round 3, there was no way to fix it after the last round, it was
built, and /trekreview called the same weakness MAJOR (MISSING_TEST).
- plan-critic, scope-guardian: rate on the review catalogue's tiers; a test
that cannot fail on a wrong implementation is major, never minor.
- plan-gate: an open MAJOR stops (PLAN_GATE_OPEN_MAJOR: revise and run the
next round; PLAN_GATE_OPEN_MAJOR_FINAL after the last round: ask the
operator). --accept-open records "build as is" after their yes, bound to
the round and the plan hash; never for a blocker.
- trekplan Phase 9: REVISE after the last round asks fix now (one extra
round) or build as is, instead of carrying the majors silently.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
voyage-lekerepo trial (2026-10-06) point 14, operator decision 2026-10-08
(«alle agenter, ny briefsjekk bare ved endring»):
- trekplan: the "Adaptive" hard rule (a 10-file project does not need 7
agents) contradicted Phase 5 ("All agents run for all codebase sizes");
it is gone, in line with quality before cost.
- brief-review-stamp.mjs: /trekbrief stamps the brief body when its
brief-reviewer gate passes; /trekplan Phase 4b skips its own review only
while the stamp is current. Stale (edited) or absent (another producer,
or a gate that did not pass) reviews as before. Additive optional
frontmatter fields, documented in Handover 1.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
voyage-lekerepo trial (2026-10-06) point 7, operator decision 2026-10-08
(«grønt merke på låsen»): the stop guard blocked Stop three times while the
executor waited for the controller, with the step's test already green.
- test-lock.mjs green --cmd "<Verify>" runs the step's test command (same
allowlist + denylist as done-line) and records green_at only on exit 0;
pending clears it; a new lock starts without it.
- stop-test-lock lets a green-marked lock stop; the write guard still
refuses the locked test files.
- trekexecute: D1 marks green after a PASS; each fix round marks pending.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
voyage-lekerepo end-to-end trial (2026-10-06), report points 8, 10, 12, 15, 16:
- approval-log: «Approve (Recommended)» / «Godkjenn (anbefalt)» is the
approval it labels; the suffix never turns a hollow answer into a yes.
- trekexecute Phase 8: the state-file block imports atomic-write through
${CLAUDE_PLUGIN_ROOT}; a relative import only ran with cwd = plugin root
(the test runs the block from another directory).
- trekreview, trekresearch, trekcontinue: stats go through stats-append like
the other commands, and a failed write is reported, never skipped
silently (closes the open STATE finding for all three). The schema
fixture's stale line refs for these and trekplan are re-measured.
- annotate prints an absolute path, so file://{$ANNOT_HTML} is a live link.
- red-proof: `red_kind` = load-error | test-failure on a proven red.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
voyage-lekerepo end-to-end trial (2026-10-06), report points 1, 5, 11:
- engine-findings: recommended_action is "Fix <file:line> so this no longer
happens: <failure scenario>", not "Resolve: <title>" (8 of 8 engine
findings were set aside as actionability:empty); the coordinator never
sets an engine finding aside for Actionability.
- findings-schema --repo-root: a cited line past the end of an existing
file is FINDING_LINE_OUT_OF_RANGE, so Phase 5's bounded re-ask fixes it
before the coordinator sees it. The reviewers' instruction said "the
actual line number from the diff"; it now says the file's own line,
never the patch's.
- fill-finding-ids.mjs: the coordinator (no shell) writes @@ID_<n>@@ and
trekreview Phase 7 computes them over (file, line, rule_key); an
unresolved placeholder or a wrong 40-hex id fails. The 4-field id with
`title` the docs named is gone; the code always used three.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
voyage-lekerepo end-to-end trial (2026-10-06), report points 2, 3, 4, 9:
11 of 13 brief criteria were NOT RUN at review with no warning in /trekbrief;
a plan `git grep` criterion passed validator, gate and three critic rounds,
then felled the run in Phase 7; the End-to-end field and Phase 7's text
search never met; a prose Verify left the test command undefined.
- criteria-runner: runnableCheck() screens a declared check without running
it (same allowlist; an npm run script is not looked up at write time);
/bin/bash tests/<script> allowed; the plan report carries end_to_end,
verified when a passed criterion runs a step's End-to-end command (the
older text form still counts).
- plan-validator 1.8: PLAN_VERIFICATION_NOT_RUNNABLE,
PLAN_STEP_VERIFY_NOT_RUNNABLE, PLAN_END_TO_END_NOT_RUNNABLE,
PLAN_END_TO_END_NOT_VERIFIED (the gate inherits them).
- brief-validator: BRIEF_SC_NOT_RUNNABLE warning; /trekbrief offers a
tests/ script; brief-reviewer no longer proposes unrunnable commands.
- trekexecute: Phase 7 copies end_to_end from the runner; Verify's test
command is its first backticked span.
Measured on the trial's own brief and plan: 11 warnings (the 11 NOT RUN),
and the plan stops on V5 git grep and the unlisted End-to-end command.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
CLAUDE.md command table: each row from its owner (trekplan from order 3,
trekexecute from order 1, trekreview from order 5).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
CLAUDE.md: the review paragraph (order 5) and the guards paragraph
(order 4) are both kept (planned union line).
The launch gate went red on the merged tree: post-approval-log reads
the session's permission_mode, and its regression test feeds that value.
Both were untracked when the branch ran its suite, so the gate never saw
them there. Operator decision 2026-10-06: a counted exemption in a new
class (mode-read: 3 + 1 hits), and the binding-rule sentence in CLAUDE.md
names it. An extra hit in either file turns the gate red again (checked).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
An independent review of abc3083 found 15 defects, the two worst verified
in scratch repos. Each fix started with a test that failed.
- Proof of red could be "proven" by the environment: a start point
unpacked with git archive had no node_modules and no .git, so any test
failed there. The start point is now a git clone --shared checked out at
start_sha, gitignored top-level entries are linked in, and a control run
(start point + the change) must pass, or the result is not-run.
- The Test first file was never committed (the template lists it apart
from Files:) and leaked into the next step's diff. The step's scope is
now Files: + test files, staged at the checkpoint.
- New files outside Files: were invisible to every check. Every untracked
file is registered with --intent-to-add; a revert unregisters them.
- The floor guard paired renames (foo.test.js -> .bak read as clean) and
missed skipIf and node's t.skip/t.todo; prose files no longer count as
stubs.
- Phase 7.5 audited from the last step's start_sha; it now uses the run's
session_start_sha.
- The done line is written after the checkpoint and checked with --commit.
- fix_rounds never passes 5; attempts are never reset; re-control keeps
the spec/quality verdicts and earlier floor-guard rulings; the closed
stop list maps every existing stop; failed vs stopped made consistent;
the controller's effort is said, not assumed.
Tests: 1470 (1468 pass, 0 fail, 2 skipped).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Wave 1, order 3 (P3 plan mode as the start, P2 design as its own part, P9
plan side). Contracts K3-K6 for the later merges.
- plan_version 1.8 (1.7 plans stay valid): Test first on every step, one
End-to-end ("run the thing") step, optional Interface in / Interface out /
Review focus fields, a ceremony class in the header (absent =
architectural), and for architectural plans a ## Design part: module map
without cycles, architecture rules that name their enforcer and the step
that proves them, a requirements check asked as keep / change.
- K3 lib/validators/plan-gate.mjs: the critic verdict is recorded INSIDE the
plan (Claude Code's plan approval hands a hook only the plan file's text),
bound to the hash taken before the reviewers read it; 0 go / 1 stop / 2
could not run; at most 3 critic rounds, then stop and ask.
- K5 lib/verification/arch-rules.mjs: runs the target repo's own
dependency-cruiser or import-linter (installs nothing; 2 = not measured,
never green); --prove --rule shows pass -> fail on a planted violation of
that rule -> pass. Verified against dependency-cruiser 18.5.0 and
import-linter 2.15; madge 8.0.0 left out (missed a planted .mjs cycle).
- K6 lib/verification/plan-scope-sweep.mjs: changed files no step names.
- /trekplan Phases 8-10: design part, bounded critic loop, the gate before
"execute", a plan-mode path through ExitPlanMode (not yet run end to end
inside plan mode). plan-critic 10 -> 12 dimensions; scope-guardian checks
the ceremony.
- Fixed on the way: plan-validator and plan-review-dedup used the
file://argv[1] main guard (no-op under a symlink or a space); CRLF plans
failed every manifest; the dedup dropped finding severity.
Borrowed, credited in place: obra/superpowers, Kiro (docs), addyosmani/
agent-skills, mattpocock/skills, GitHub Spec Kit, bashebr/ai-native-sdlc,
Boris Cherny's public threads.
Suite 1497 (1495 / 0 / 2), 86 new tests.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
