voyage/agents
Kjell Tore Guttormsen 8e3946e687
feat(research): researching-sources skill, preloaded by the five web agents
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>
2026-10-08 21:46:49 +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 fix(review): the review keeps the findings that are right 2026-10-08 06:48:13 +02:00
brief-reviewer.md fix(validate): a check that can never run is caught when the brief or plan is written 2026-10-08 06:42:33 +02:00
code-correctness-reviewer.md fix(review): the review keeps the findings that are right 2026-10-08 06:48:13 +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 fix(agents): no agent is pinned below the high floor 2026-10-05 17:40:53 +02:00
plan-critic.md fix(plan): an open MAJOR stops the plan; after the last round the operator decides 2026-10-08 07:07:00 +02:00
planning-orchestrator.md feat(plan): plan 1.8, the plan gate, the design part and the plan-side checks 2026-10-06 20:10:57 +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 fix: close what an independent review found in the trial 2 fixes 2026-10-08 15:21:56 +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 fix(plan): an open MAJOR stops the plan; after the last round the operator decides 2026-10-08 07:07:00 +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: close the six defects an independent review found in the trial fixes 2026-10-08 07:17:45 +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