1. plan-review-dedup skips only a null or undefined finding; any other
entry that is not an object (a string, a number, an array) goes on as
before E, a finding with no valid severity that the plan gate counts as
a blocker (it was dropped, so a string blocker recorded PASS).
2. plan-gate --record: a previous finding that rule A carried as counted and
whose id is backed this round leaves the counted set, the counts, the
verdict and the stop rule's summary (it was counted and listed in
known_outside at once: BLOCK, not-fewer, and --accept-open refused).
3. A known_outside entry keeps rule_keys; extractVerdict accepts it (a list
of strings), and the bare gate re-checks with the same keys the recorder
used, so a merged finding whose security key is only in rule_keys is a
WARN, not a STOP.
4. plan-critic, scope-guardian and /trekplan Phase 9's round-2 sentences say
the Critic Verdict also lists known_outside and each is marked by id in
previous. Code already accepts such a mark (dedup passes it; countRound
ignores ids it does not carry; --record removes the entry on true);
pinned in diff mode and full count.
5. The approval prose names ## Threat Model where it named only ## Intent +
## Goal: skills/annotating/SKILL.md (description, step 4, guard list),
docs/command-modes.md, Handover 1's intent_approved_hash row, README
(approval, Approve row, intent approval gate) and CLAUDE.md's /trekbrief
row.
6. threat-model.mjs gains usableInRepo (a brief path relative to the repo
top level) and repoRelativeBrief; --record stores brief_path relative to
the top level, never absolute, and both gates read it from there, so the
gate run from a subdirectory reads the same brief. reviewThreatModel
uses usableInRepo. Handover 4 and the gate header say so.
7. review-finalize's outside pass puts an entry back only when no finding
carries its row yet (engine-compare rowOf): an engine finding listed in
known_outside while its payload is saved went back twice.
8. A test runs scripts/release-check.mjs on a review whose known_outside
entry the brief does not back: exit 2 (control: backed passes the review
check).
Existing tests changed: plan-gate-threat-model's entry-keys assertion now
expects rule_keys (item 3), and its planted non-security entry drops the
security key from rule_keys too, since the gate reads rule_keys (item 3).
Part 2 fix round of the E plan.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The code-correctness reviewer's dimension 6 shrinks to what the engines do
not read: command, skill and agent markdown carrying shell, with Claude
Code's threshold (a concrete attack path, high confidence), the keys
SECURITY_INJECTION or SECURITY_RISK, and threat_model_ref quoting the
brief's Outside: line; the code-level bullets go to the engines.
The coordinator puts a Voyage security finding with a threat_model_ref
into the trailing JSON block's known_outside, never into findings.
review-finalize gains the pass `outside`, right after engine: it only
raises. An entry the brief at the review's brief_path does not back now
(line gone, threat model not usable, an engine finding, not a security
finding) goes back into the findings at its catalogue tier with a Source
line, R-step and raised verdict, as the engine put-back does; the rest are
listed under the new `## Outside the Threat Model` section.
verdict-gate decideOpenFindings (and so scripts/release-check.mjs)
re-checks every entry against brief_path through the new
notBackedOutside and exits 2 for one not backed. review-validator
shape-checks the optional known_outside (REVIEW_KNOWN_OUTSIDE_MALFORMED).
threat-model.mjs gains reviewThreatModel and isKnownEntry for the three.
/trekreview Phase 8.8 lists the known issues outside the threat model
(not answered, not counted); the review template shows the section and
field; Handover 1 names the optional ## Threat Model and its code,
Handover 6 names known_outside and its code.
Part 2, step 2.5 of the E plan.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
plan-gate.mjs --record --brief <brief.md> (a known flag; its value is kept
out of the positional arguments, a missing value is a usage error) applies
the brief's threat model to the deduped findings before countRound when
threat-model.mjs usable() says it may: a backed finding (Voyage's own
security finding whose threat_model_ref equals an Outside: line's text)
leaves the counted set and the stop rule and goes to the new optional
verdict field known_outside ({id, rule_key, text, line}), carried to later
rounds until a reviewer marks it resolved or it is reported again under its
id. The verdict stores brief_path (carried when a later round has none).
The --record line adds known_outside (a count) and threat_model
({applied, why}): a threat model that is not usable backs nothing, every
security finding counts, and the output says why. extractVerdict
shape-checks both new fields.
The bare gate re-reads the brief at brief_path each run: an entry still
backed is a warning, PLAN_GATE_KNOWN_OUTSIDE; one no longer backed (line
gone, approval stale or not logged, brief unreadable, no brief_path, or not
a Voyage security finding) stops the plan, PLAN_GATE_OUTSIDE_NOT_BACKED: it
counts in full. gatePlan takes an optional threatModel for tests.
plan-review-dedup keeps threat_model_ref on a merge only when every merged
copy carries the same one; the S160 known issue is fixed: a null in a
reviewer's findings list is skipped instead of crashing the CLI.
plan-critic and scope-guardian: a security finding needs a concrete attack
path and high confidence (Claude Code's threshold, 167), uses
SECURITY_INJECTION or SECURITY_RISK, and quotes the Outside: line's text in
threat_model_ref when one applies; the json template carries the field.
/trekplan Phase 9 passes the brief path to plan-critic and --brief to
--record. Handover 4 names the two fields, the two codes and the flag.
Part 2, step 2.4 of the E plan.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
lib/review/rule-catalogue.mjs gains SECURITY_RISK (BLOCKER, category
security, memory route rule): Voyage's own security key for a finding by
its own reviewers that SECURITY_INJECTION does not cover.
SECURITY_REVIEW_VULNERABILITY is described as the engines' key only.
plan-critic and scope-guardian name SECURITY_INJECTION or SECURITY_RISK
and no longer the engines' key.
The count moves from 17 to 18 in every pin: rule-catalogue.test,
claude-md-scope [CAT] (which now also refuses a stale 17), doc-consistency,
review-prose-pins, docs/architecture.md and the two reviewer agents.
critic-severity-rules pins three security keys; its "every security key
named" check leaves out the engines' key, and a new pin says the critic
never names it.
Existing tests changed for the planned rule: the four count pins above
(17 -> 18), and critic-severity-rules' two-key test (now three keys).
tests/lib/engine-findings.test.mjs: a comment naming the "(17 keys)" pin
now says 18.
Part 2, step 2.3 of the E plan.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
/trekplan Phase 9: when --record or the gate reports the stop rule there
is no new round; AskUserQuestion with the class and counts, "Known issue"
(--accept-open, a security finding refused) or "New mechanism" (stop, the
plan stays unapproved); the round-3 blocker path never offers
--extra-round after the stop rule. Phase 10 prints round of
max_rounds + extra_rounds.
/trekexecute Phase 7.2 step 4: after a round-2 BLOCK or fixed-pending,
before any R-step, review-rounds.mjs prepare --dry-run; review-stop-rule:
gives the same question ("Known issue" = /trekreview --answers, a BLOCKER
keeps the merge locked; "New mechanism" = stop). /trekreview Phase 3 tells
the stop rule's exit 1 from the cap's. plan-critic and scope-guardian:
rule_key names the class, never the instance.
New pins in review-loop-docs, critic-severity-rules and review-prose-pins.
Part 1, step 1.4 of the E plan.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The four profiles, the resolver, the profile validator and docs/profiles.md go;
/trekbrief Phase 3.5 and the brief's phase_signals checks go (an older brief's
key is ignored); MANIFEST_PROFILE_DRIFT and profile_used go. Every Profile,
Composition rule, Sequencing gate and High-effort section leaves the commands.
Decision 209: /trekresearch runs the full swarm with contrarian-researcher as
wave 2 every run; /trekreview and the coordinator run all four passes with no
high-effort normalization. Voyage agents are spawned with no model (their own
model: opus applies); the two built-in spawns pass model "opus". --profile
stays in the parser as a retired flag that swallows its value. §Model & effort
moves to docs/architecture.md; the sequencing-gate eval case goes.
Files removed: 44 (43 from the R3 list + tests/commands/trekreview.test.mjs,
whose every test pinned removed text). Files edited: 43.
Tests: 2467 (2466 pass / 0 fail / 1 skipped) before, 2309 (2309 pass / 0 fail /
0 skipped) after. Durable check: all three groups green, none pending.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
R4-R7 of the cleanup list (decision 188): the June trial docs and
fixtures, the three orchestrator reference docs, the dormant
synthesis-agent, code with no caller (project-discovery, bash-normalize,
fidelity-diff, test-census, the next-session prompt validator, arm B and
the --workflow flag) and the fix-round chain. Living docs repointed; the
reasons for in-session orchestration and the all-opus pin are now written
in docs/architecture.md and docs/profiles.md.
New tests/lib/living-paths.test.mjs: living tracked text names only
plugin paths that exist (seen red with 22 dead pointers before this
commit). docs/T1-cc26-delegated-orchestration.md and
lib/review/gold-scorer.mjs stay until R-b: the frozen end-state registry
names them.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Pass 1 merged two different /code-review findings on (bin/slug.mjs, 46, CODE_REVIEW_DEFECT) and the second lost its row and its action. A reviewer never duplicates itself: its second finding on a triplet under another title stays its own row, with the id over rule_key#2 (the form critic-diff already uses); fill-finding-ids counts the same way (voyage-lekerepo trial 5, finding 7).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A brief success criterion and a plan's Verify, Regression, End-to-end and
Verification lines are each one command the criteria runner accepts, written
as the line's first backticked span; anything more is bash tests/<name>.sh,
and each must be able to go red (the runner reads the exit code only).
- skills/writing-criteria/SKILL.md (S1 form), with Runs:/Refused:/Never red:
examples that a pin runs through the criteria runner
- brief-reviewer and plan-critic preload writing-criteria and
reviewing-adversarially (S3 + S4); the copied runner rules leave them, the
two templates and /trekplan, which names the skill where the plan is written
and where its three reviewers start
- eval cases 3 fire / 2 quiet / 1 effect; tests/lib/skills-criteria-prose-pins
- review-630 @~1 pin follows the text into the skill; trekplan-stats line_ref
re-measured
Baseline without the skill: 24 of 27 written checks refused by the runner,
and 0 of 3 reviewers saw that git status/git log can never go red. With it:
0 of 27 refused, 3 of 3 reviewers flagged both.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A new skill, voyage:reviewing-adversarially (contract S4): no praise, no
finding without a source (file:line or a quoted line), no downgrade without
a reason, summary-only said and not judged, a Declined to Judge list, claims
checked against the diff rather than the report, axes kept separate.
Red baseline first: six review runs by helpers without the skill (two
invented fixtures) had no separate Declined to Judge list in 6 of 6, an
unsourced finding in 6 of 6, praise in 2 of 6 and a verdict on something
unmeasured in 4 of 6. With the skill: 6 of 6, 0, 0 and 0.
- brief-conformance-reviewer, code-correctness-reviewer, review-coordinator
and scope-guardian preload it through skills:; the 21-line "Interaction
Awareness - MANDATORY OVERRIDE" block copied into three of them is gone.
Each agent keeps its own role.
- The two reviewers and scope-guardian end with their own Declined to Judge
list; /trekreview names the skill at spawn and passes the reviewers'
lines to the coordinator, which copies them into review.md as prose
(the JSON declined_to_judge array and the verdict are unchanged).
- Eval cases 3 / 2 / 1; pins in tests/lib/skills-review-prose-pins.test.mjs.
- tests/fixtures/jsonl-schemas.md: the trekreview-stats line_ref moves with
Phase 8 (636-686).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
An engine's brief-conflict mark could lower a reviewer agent's MAJOR: ingest kept an engine field a reviewer wrote on its own finding, and on a severity tie the survivor depended on payload order (engine first gave ALLOW, reviewer first WARN). ingest now takes engine from the payload source; Pass 1 and the workflow dedup keep the reviewer-agent finding on a tie. Prose (coordinator Pass 1, Handover 6) follows. Decision 13, operator 12.10.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Round 8 (0f400d3..29b4ac9, BLOCK: 1 BLOCKER, 12 MAJOR, 1 MINOR). Each fix
began with a test that failed on 29b4ac9 (13 tests, all red there); suite
2221 (2219/0/2).
- BLOCKER: a backticked check whose trailing comment holds a quote, $,
backtick or backslash is refused, not dropped. The comment was never
screened, while the executor hands the Verify span as written to red
proof, the test lock and the done line inside --cmd "...", where a $(...)
runs and a quote ends the argument. trekplan's text and the reviewer's
NOT RUN table say so.
- A span that is only a comment is not-a-command, not a placeholder. The
dropComment text says the allowlist still refuses a word with a # in it.
- The criteria runner, comparison-gate and end-state-gate use isMain: they
did nothing and exited 0 under a symlinked path. The test now refuses any
process.argv[1] comparison outside lib/util/is-main.mjs.
- Files: in a field with backticked paths, a plain word counts only before
the entry's description (a dash, or a colon after the path); a name with
no slash only first in its entry or after and/or/+/&. "mocks
fs.readFileSync", "runs on Node.js 22.x" or "no change to package.json"
no longer make a tests-only step look like it builds something.
Lowercase makefile, rakefile and justfile are build files. Measured on the
520 Files: fields in 48 plans of the marketplace and the test repo:
3 fields read differently (two notes no longer read as files, one
duplicate name dropped), tests-only changed in 0.
- The test lock compares --cmd without its trailing comment, and the test
lock and the done line read a stop with stoppedBy, the one reading.
red-proof drops its second reading, spawnError.
- release-check reads a relative --review in --repo or, when only that one
exists, from the current directory as 6.3.0 did; two different files are
exit 2, never guessed. The runbook says so.
- One trailing-json reader: a closing fence may be longer than three
backticks, in the block reader and the verdict gate alike, and the review
validator and the synthesis digest use it, so three backticks inside a
JSON string no longer hide a BLOCKER from the remediation-step check.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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>
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>
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>
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>
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>
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>
