evolve
Skill4 starsChanged 3 months agoApache-2.0View on GitHub
One iteration of the harness self-improvement loop - digest the session journal, pick the single highest-friction pattern, make ONE surgical patch to a harness artifact (CLAUDE.md, a hook, skill, agent, or lessons promotion), pass the lint gate, commit. Run via /loop or a Routine for continuous improvement, or invoke once as /evolve.
43 other projects use a version of this.
Adopted by
Most recently taken up by
- Renozoic-Foundry/forge-publictheir own version, first seen Nov 15, 2026
- DataArt/artisyn-implementation-harnesstheir own version, first seen Nov 15, 2026
- aemerson-commits/shareable-skillstheir own version, first seen Nov 13, 2026
- morodomi/dev-crewtheir own version, first seen Nov 12, 2026
- SethGammon/Citadeltheir own version, first seen Nov 4, 2026
- vidit19sharma/neogentstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use instinct-export, instinct-import and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
TheKREATORSSkillinstinct-export
Export instincts from project/global scope to a file
Also in 4 projects that use this
TheKREATORSSkillinstinct-import
Import instincts from file or URL into project/global scope
Also in 4 projects that use this
AWSSkillmap
Map verified service capabilities against customer-provided control framework and threat model. Produces mapping-results.json, controls-catalog.md, and framework-mapping.md. Supports pluggable frameworks: CCMv4, NIST 800-53, CIS Benchmarks, ISO 27001, etc. Split into 4 focused sub-skills for better accuracy; this skill orchestrates them.
Also in 5 projects that use this
diego-tobalinaSkillbuild-fix
Fix build and compilation errors systematically. Run when build fails.
Also in 3 projects that use this
launch52-aiSkillskill-create
Create and validate Claude Code skills with proper structure, checklists, and validation scripts. Use when creating a new skill, auditing existing skills, or ensuring skills meet quality standards. Generates complete skill scaffolds with SKILL.md, check scripts, guides, and templates.
Also in 3 projects that use this
qtzx06Skilleval
Evaluate trained YOLO model accuracy with mAP metrics and per-class error analysis. Identifies failure cases for targeted improvement. Use after training.
Also in 5 projects that use this
- +1 more from TheKREATORS
Other versions43 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 43
- revfactory/harness★ 9.1ksame name
- Q00/ouroboros★ 6.4ksame name
- yologdev/yoyo-evolve★ 1.9ksame name
- iovisor/ubpf★ 997same name
- SethGammon/Citadel★ 927same name
- GAIR-NLP/ASI-Evolve★ 867same name
- Snowflake-Labs/coco-skills★ 54same name
- Kanevry/session-orchestrator★ 53same name
- mycelium-hq/ai-brain-starter★ 50same name
- unclejobs-ai/second-claude-code★ 41same name
33 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .codex/AGENTS.mdAGENTS.md
- api-ts/CLAUDE.mdCLAUDE.md
- bot/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- showcase/CLAUDE.mdCLAUDE.md
- webapp/CLAUDE.mdCLAUDE.md
- gitbook/llms.txtllms.txt
- suwappubot-conventionsSkill
- aegis-goalSkill
- design-iterateSkill
- ethglobal-goalSkill
- goalSkill
- handoffSkill
- redesign-existing-projectsSkill
- reflectSkill
- suwappubot-conventionsSkill
- design-taste-frontendSkill
- suwappuSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 37 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
User-stated friction: if this run was invoked with a focus hint (/evolve <hint> — the hint outranks the digest).
- Distinctive: line 30
If the digest is empty AND there's no hint and no recidivism: report "no signal, no change" and STOP.
- Very specific: line 61
Must print PASS. If you added/changed a hook, also smoke-test it: echo '{}' | python3 .claude/hooks/<hook>.py.
- Distinctive: line 63
If the gate fails, fix or revert — never commit a failing harness.
“Common” is measured: kept by at least 6 in 10 of the 37 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/evolve — one self-improvement iteration
Design: docs/harness/self-improving.md (Hermes self-evolution + pi-reflect patterns). Loop shape: evaluate → reflect → patch → verify → commit. One iteration = ONE change. Small surgical diffs beat rewrites; the git log is the audit trail and the rollback mechanism.
1. Evaluate — read the evidence, never guess
python3 scripts/harness/journal_digest.py --days 30
git log --oneline -15 -- .claude/ CLAUDE.md
git log --oneline -- .claude/harness/lessons.md | head -20Evidence sources, in priority order:
- Recurring error buckets in the digest (same failure across 2+ sessions).
- Recidivist lessons — a lessons.md section edited 3+ times means prose isn't working; it needs promotion to an enforcing artifact.
- Denial-heavy sessions — repeated permission prompts → allowlist candidates
for
.claude/settings.jsonpermissions. - User-stated friction if this run was invoked with a focus hint
(
/evolve <hint>— the hint outranks the digest).
If the digest is empty AND there's no hint and no recidivism: report "no signal, no change" and STOP. An evolution loop that edits without evidence is noise.
2. Reflect — pick ONE target and the right artifact type
Match the friction to the artifact that enforces the fix, preferring the most mechanical option (top = strongest):
| Friction pattern | Patch target |
| Model keeps doing a forbidden/broken thing | New or edited hook in .claude/hooks/ + settings.json |
| Multi-step procedure keeps going wrong | Skill in .claude/skills/<name>/SKILL.md |
| Wrong specialist/model routing | Agent def in .claude/agents/ or routing table in CLAUDE.md |
| Permission prompt friction | permissions.allow in .claude/settings.json |
| Repo fact the model keeps rediscovering | .claude/harness/lessons.md ## Facts |
| Judgment rule with no mechanical enforcement | CLAUDE.md (mind the 4000-word budget — merge, don't append) |
3. Patch — surgical rules
- ONE artifact change per iteration (plus its
settings.jsonwiring if a hook). - Edits over rewrites. Never restructure a file you're not fixing.
- New hooks: must exit 0 on any internal error (never break sessions), parse
under
python3 -c "import ast; ast.parse(open(f).read())", and follow the style of.claude/hooks/session-journal.py. - Deleting/evicting: quote what you removed in the commit body.
4. Verify — the gate is not optional
python3 scripts/harness/harness_lint.pyMust print PASS. If you added/changed a hook, also smoke-test it:
echo '{}' | python3 .claude/hooks/<hook>.py; echo "exit=$?" → must exit 0.
If the gate fails, fix or revert — never commit a failing harness.
5. Commit
HUSKY=0 git add <changed files>
HUSKY=0 git commit -m "harness(evolve): <what changed and which friction it kills>"Push only if the user asked for it or a Routine/loop invocation says to.
Continuous mode
- Manual cadence:
/loop 1h /evolve(stops when you stop the loop). - Scheduled: a Routine/cron firing
/evolveweekly is the sane default — the journal needs sessions to accumulate between iterations. - Convergence check every ~5 iterations: if recent
harness(evolve)commits keep touching the same artifact, the loop is thrashing — stop and surface it to the user instead of patching again.
Output
Reply ≤8 lines: evidence chosen, artifact patched (path), one-line diff summary, lint result, commit hash. If no-change: the one line "no signal, no change."
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

