The coupling to Claude Code's built-in run skill (wave 4, order A2,
decisions 54 and 64). The plan's "run the thing" step, the executor's
End to end part and the plan template each say in one sentence that the
app is seen and driven with run, and that the verdict is still the
End-to-end: command, because run gives no exit code. The template quotes
the name instead of backticking it: every backticked span on a template
step bullet is read as a runnable example.
R2: lib/skills/routing.mjs keeps a short fixed list of Claude Code's own
skills a quiet case may name as owner (BUILTIN_OWNERS, only run, seen in
2.1.303). For such an owner only "not taken" is checked, and the report
says so; ROUTING_NEGATIVE_WON stands, and an owner on no list is still
ROUTING_UNKNOWN_OWNER. skill-writing-criteria-quiet-2 gets owner=run.
The trekplan.md paragraph is reflowed to its old line count so the stats
line_ref there does not move (order B edits the same file); the
trekexecute Phase 9 line_ref fixture moves by two lines.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
P10's model-free part (wave 4, order A1, decision 63). The routing test now
checks every case in evals/ for from=, not only the skill-tagged ones (R1):
a case with no skill tag is not routed, only checked, and the report gives
both counts ("45 cases checked for from=, 37 routed"). The eight test-set
cases get from=proevesett-eval-suite (d311f3b) or
from=proevesett-intent-gate (3892a83), the commits that added them.
The release gate that reads the last test-set run is written into the
runbook as exempted with its reason (it waits for the fixed test set to run
again) and still says where it goes (scripts/release-check.mjs).
review-630's prototype-tag stub gets from=test: under R1 an unrouted case is
still checked for from=, and the stub tests that a prototype name is never
routed, which stands.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
/trekbrief Phase 3 carried the interview form inline. It now asks for the
new skill voyage:interviewing by name (allowed-tools gains Skill) and keeps
only its own contract: the size class and budget, the three fixed questions
(framing first, class, storage), where each answer lands in the brief, and
the answers that decide nothing. Step 3a and the form points of Step 3c move
into the skill with their credits (Pocock, Osmani, Spec Kit; licences and
line ranges checked at the pinned commits).
Red baseline first (3 helper interviews against a fixed answer sheet,
Opus 5.5): 10-11 questions in round 1 (3 of 3), 15 of 31 without a
recommendation, a hollow answer written in as a decision (2 of 3), unasked
scope as a requirement (2 of 3). With the skill: 4, 0 of 12, 0 of 3, 0 of 3.
Fact questions and stopping did not fail without it.
Also: pointers to voyage:writing-criteria (S3) where criteria are asked and
written, both review skill names (S3 + S4) in the brief-reviewer prompt; the
intent pins that read moved text now read the skill, same assertions; the
Phase 7 line_ref moves with the shorter Phase 3; 7 eval cases (3/2/2).
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>
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>
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 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>
Both patterns now start at the beginning of the reply ((?<![\s\S]), which
holds with or without a multiline flag) and refuse the whole reply when it
carries the opposite verdict in capitals (FAIL/FAILED for says-pass,
PASS/PASSED for says-fail), unless negated. The opposite word in lower case
does not refuse: correct case-6 replies say "did not pass" and, once on
687710a, "The other checks passed".
Chosen: refuse only the capitalised opposite, because refusing it in any
case would fail correct replies again, the instability this change removes.
Measured on 22 case-8 and 14 case-6 recorded replies (PM re-measurement +
this session): old says-pass 19/22, new 22/22; old says-fail 13/14, new
14/14; each grader on the other case's replies 0.
Suite after git add: 1236 tests, 1234/0/2.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Case 8 failed 2 of 12 in the PM re-measurement of ea66a98 on correct replies
that said "passed" without PASS. The patterns now spell each letter as a
class ([Pp][Aa][Ss][Ss]...) instead of relying on a regex flag, since a grader
file carries only `pattern`. The verb forms pass/passes/passed and
fail/fails/failed are verdicts; a preceding "not " or "n't " still refuses.
Measured on the PM's recorded replies (distinct runs): old says-pass 10/12 on
case 8 (reproduces the finding), new 12/12; says-pass on case 6 replies 0/8
both, says-fail 8/8 on case 6 and 0/12 on case 8 both.
Suite after git add: 1235 tests, 1233/0/2.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
New grader names-code (regex, trace, code\W{1,12}BRIEF_V51_MISSING_SIGNALS),
the same form as the intent case's names-code. It checks what the case's
expected_outcome promised before any run: the validator reports the code.
Checked on this session's recorded traces before the commit: it matches
10 of 10 green runs and 0 of 3 runs with the check disabled.
Known-positive re-run in the scratch copy (validator check 'if (false)'):
0 of 3 cases pass, names-code fails in each, the other 5 graders pass.
Green: tests/lib/proevesett.test.mjs 10 of 10.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The scaffold writes a current intent_approved_hash (sha256 over ## Intent +
## Goal) into the case-4 brief. Chose a literal marker over running
intent-approval.mjs --stamp in the scaffold because --stamp emits a
brief-approved record into the live stats the yardstick reads: every eval
run would count as an approval.
New grader no-intent-halt (regex, trace, not_contains
code\W{1,12}BRIEF_INTENT_): a halt at the intent gate fails the case
instead of passing it for the wrong gate.
says-fail / says-pass take FAILED / PASSED as the verdict word. v2's word
boundary dropped them. The one says-fail failure (PM, 1 of 7) is not
explained: its trace was deleted, and 0 of 13 kept replies used another
spelling than FAIL.
Case 4 alone, 10 runs: 10 of 10. In 3 of 10 the child ran the intent gate
first, passed it and went on to the brief-validator. That order halted the
case before. Before the fix, same day: 5 of 6.
Green: tests/lib/proevesett.test.mjs 9 of 9.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
New case plan-halts-without-intent-approval (expectation committed before
its first run): a 2.1 brief WITH phase_signals and no intent marker.
Graders: intent-approval.mjs --check ran; the trace carries the gate's own
JSON code for BRIEF_INTENT_NOT_APPROVED; no Agent; no plan.md.
review-requires-project: the arg parser now has a CLI that checks the
required flag and prints 'Error: --project <dir> is required.' + usage
(exit 1, code ARG_REQUIRED_MISSING). trekreview.md runs it with
$ARGUMENTS (it passed "$@", which the Bash tool never has, so the parser
never ran — 0 Bash calls in the PM's case-5 traces) and relays its stderr
instead of composing the line. The grader project-required (reply regex,
unstable on backticks) is replaced by parser-ran + names-missing-project
(trace, the parser's JSON code), the same form as names-rule.
Graders: no-error-code is bound to the validator's JSON output form and
covers every REVIEW_* code (WRONG_TYPE and VERSION_FORMAT were missing);
says-pass/says-fail reject a preceding NOT and a longer word; every case
with no-write also gets no-bash-write (redirect, tee, touch, cp, mv, rm,
sed -i in the Bash command). Checked on the PM's 10 recorded traces: no
false positive; known-positive/negative still split.
Red 348aa95 6/7 → green 7/7. Suite 1231: 1229 pass / 0 fail / 2 skip.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Offline structure tests for evals/ (the suite itself needs headless runs):
- no case reaches the steg 1 intent gate (PM: 0 traces touched it). The
new case's scaffold is in: its brief passes brief-validator --soft
(2.1 WITH phase_signals) and --check gives BRIEF_INTENT_NOT_APPROVED —
that test is green, so the fixture reaches the gate.
- review-requires-project: trekreview.md composes 'Error: --project <dir>
is required.' in prose (8/10 in the PM run, backticks broke the regex),
and its arg-parser line passes "$@", which the Bash tool never has.
- no-error-code misses REVIEW_WRONG_TYPE; PASS/FAIL graders are raw
substrings; no-write cannot see a write through Bash.
7 tests, 6 red.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Seven `claude plugin eval` cases under evals/, runs: 1, deterministic graders
only (regex, tool_used, file_exists), no ablation. Each case tests one thing
Voyage promises and stops within minutes, headless:
- plan-requires-brief, plan-project-not-initialized, plan-rejects-unknown-export,
review-requires-project: argument guards stop before any Agent or Write.
- plan-halts-without-phase-signals: a brief_version 2.1 brief without
phase_signals halts /trekplan at the sequencing gate, before the swarm.
- review-validate-flags-bad-finding-id (known-positive) and
review-validate-passes-clean-review (known-negative): /trekreview --validate
names REVIEW_BAD_FINDING_ID on a planted bad ID and stays clean on a valid file.
Each case's expected_outcome is committed here, before the suite has run.
Fixtures are written by an inline scaffold.sh (needs --scaffold): chose inline
heredocs because a run cannot read the eval directory, and the add_dirs path
mapping is not documented. evals/results/ is ignored.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
