voyage/agents
Kjell Tore Guttormsen f906ec9252
feat(skills): reviewing-adversarially, one stance for every reviewer
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>
2026-10-17 07:34:08 +02:00
..
architecture-mapper.md fix(agents): no agent is pinned below the high floor 2026-10-05 17:40:53 +02:00
brief-conformance-reviewer.md feat(skills): reviewing-adversarially, one stance for every reviewer 2026-10-17 07:34:08 +02:00
brief-reviewer.md fix: round 7 of the release review of 6.3.0, for 6.3.1 2026-10-11 09:11:57 +02:00
code-correctness-reviewer.md feat(skills): reviewing-adversarially, one stance for every reviewer 2026-10-17 07:34:08 +02:00
community-researcher.md feat(research): researching-sources skill, preloaded by the five web agents 2026-10-08 21:46:49 +02:00
contrarian-researcher.md feat(research): researching-sources skill, preloaded by the five web agents 2026-10-08 21:46:49 +02:00
convention-scanner.md refactor(agents): relocate example blocks to body (retrieval agents) 2026-06-29 10:16:48 +02:00
dependency-tracer.md fix(agents): no agent is pinned below the high floor 2026-10-05 17:40:53 +02:00
docs-researcher.md feat(research): researching-sources skill, preloaded by the five web agents 2026-10-08 21:46:49 +02:00
git-historian.md feat(trekplan): Regression and On failure step rules, and trial 2's minor fixes 2026-10-08 21:42:21 +02:00
plan-critic.md fix(plan): plan-critic and scope-guardian state rule B, mark previous findings and tag security findings 2026-10-16 01:06:42 +02:00
planning-orchestrator.md docs(plan): Phase 9, Handover 4 and CLAUDE.md name rule A, with door lines 2026-10-16 01:34:51 +02:00
research-orchestrator.md release(v5.10.1): drop gemini-bridge from the pipeline; correct the T1 §6 PoC status 2026-09-03 20:29:39 +02:00
research-scout.md feat(research): researching-sources skill, preloaded by the five web agents 2026-10-08 21:46:49 +02:00
review-coordinator.md feat(skills): reviewing-adversarially, one stance for every reviewer 2026-10-17 07:34:08 +02:00
review-orchestrator.md feat(review): the review is a gate - verdict in the file, CC engine, project memory 2026-10-06 19:45:52 +02:00
risk-assessor.md refactor(agents): relocate example blocks to body (reviewer/planning agents) 2026-06-29 10:19:24 +02:00
scope-guardian.md feat(skills): reviewing-adversarially, one stance for every reviewer 2026-10-17 07:34:08 +02:00
security-researcher.md feat(research): researching-sources skill, preloaded by the five web agents 2026-10-08 21:46:49 +02:00
session-decomposer.md feat(execute)!: hand waves over as session orders, never start Claude Code (green) 2026-09-27 15:35:22 +02:00
step-implementer.md fix(execute): below 1.8 a plan that names no test file gets the files the helper wrote 2026-10-14 18:17:24 +02:00
synthesis-agent.md chore(voyage): release v5.6.1 — one-line descriptions for reference/dormant agents (~700 tok trim) 2026-06-24 11:52:59 +02:00
task-finder.md fix(agents): no agent is pinned below the high floor 2026-10-05 17:40:53 +02:00
test-strategist.md refactor(agents): relocate example blocks to body (retrieval agents) 2026-06-29 10:16:48 +02:00