feat(v12.1.0): harvest workflow-capture skill; revert Fable promo default to opus[1m]#123
Merged
Conversation
…ault to opus[1m] New /harvest skill (36 -> 37): captures an unusually good workflow from a stronger or temporary model, a one-off session, or a teammate's transcript into a reviewed artifact (skill, rule, profile, AGENTS.md diff, or team learning), extracted as procedure + failure modes + quality bar + self-tests, routed to the smallest artifact that carries it, and validated with 2-3 blind trap prompts before an approval gate on anything shared. Fable promo window closed on schedule: config/10-core.json session default reverted fable -> opus[1m] (pre-announced in 11.30.5); agent-models.md and MANUAL.md promo notes moved to past tense. Supersedes #122.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What this does
Adds a
/harvestskill that saves a great workflow before it disappears — when a stronger or temporary model, a one-off session, or a teammate's transcript produced behavior worth keeping, this turns it into a reviewed cc-settings artifact instead of a memory. It also closes out the Fable promo on schedule: the shipped session default returns toopus[1m].Summary
skills/harvest/SKILL.md(36 → 37, cap 40): six phases — identify what's harvestable (repeatable procedure, not raw intelligence), gather evidence (interview or transcript analysis), extract procedure / failure modes / quality bar / self-tests, route to the smallest artifact (skill, rule, profile, AGENTS.md, or/share-learning), write per the target's conventions, validate with 2–3 blind trap prompts (autoresearch blind-run rule). Hard approval gate before touching shared standards or posting team knowledge. Non-goals: no model-API sampling, no operating-manual prose.ACTIVE_SKILLS, MANUAL.md (section + All Skills row), skill counts bumped 36 → 37 in CLAUDE.md / CLAUDE-FULL.md / MANUAL.md.config/10-core.jsonfable→opus[1m];docs/agent-models.mdheader and MANUAL.md default-model note past-tensed. Agent pins already onopus[1m], unchanged. Supersedes chore: revert Fable 5 promo default (promo ended July 7) #122 (same config line, no docs/changelog).src/setup.ts+.claude-plugin/plugin.json, kept in sync per the manifest test), CHANGELOG entry.Test Plan
bun run lint:skills— 37 skills, 0 errorsbun run typecheckbun test— 767 pass, 0 fail