Records atomic learned behaviors with confidence scores. Project-scoped instincts are isolated per project and auto-promote to global scope at confidence threshold 0.8. Stores instincts in .claude/context/memory/instincts.jsonl
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Une commande directe contourne le prompt de vérification. Examinez la source avant de l'exécuter.
Records atomic learned behaviors with confidence scores. Project-scoped instincts are isolated per project and auto-promote to global scope at confidence threshold 0.8. Stores instincts in .claude/context/memory/instincts.jsonl
["Record instincts immediately after observing a reliable pattern","Keep instinct text atomic — one behavior per record","Set confidence honestly; overconfidence poisons the global pool","Review promoted instincts for cross-project validity before relying on them"]
error_handling
strict
source
builtin
trust_score
100
provenance_sha
6bed08492dc2f1d0
Instinct Learning
Overview
Instinct Learning records atomic learned behaviors as structured instinct records. Each instinct has a confidence score (0.3–0.9), a project scope, and a promotion pathway to global scope when confidence reaches 0.8.
This prevents knowledge from evaporating between sessions and stops cross-project contamination by isolating low-confidence instincts in the project that generated them.
When to Use
Invoke when:
An agent observes a reliable pattern that should influence future behavior
A debugging session surfaces a non-obvious fix that will recur
A workflow succeeds repeatedly and should be encoded as a default
An error pattern is identified that should be avoided project-wide
Skill({ skill: 'instinct-learning' });
Iron Law
NO INSTINCT WITHOUT AN OBSERVED BASIS.
Every instinct record MUST include `source_context` describing the observation
that generated it. Invented instincts are worse than no instincts.
Confidence Scale
Score
Meaning
Promotion Eligible
0.3
Seen once, uncertain
No
0.4
Seen twice, possibly coincidental
No
0.5
Consistent in this project
No
0.6
Reliable in this project
No
0.7
Highly reliable, limited cross-test
No
0.8
Auto-promotes to global scope
YES
0.9
Canonical — applies across projects
YES (immediate)
Instinct Record Schema
Each record in .claude/context/memory/instincts.jsonl follows this structure: