메뉴
One-command auto-seed from Claude Code session history. Scans ~/.claude/projects/**/*.jsonl, aggregates user-typed directives, runs extract → signature.json active. The default onboarding path.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | init |
| description | One-command auto-seed from Claude Code session history. Scans ~/.claude/projects/**/*.jsonl, aggregates user-typed directives, runs extract → signature.json active. The default onboarding path. |
| user-invocable | true |
| allowed-tools | ["Bash","Read","Write"] |
The default first-run experience for CogSig. Scans the user's existing Claude Code session history, aggregates user-typed directives into a dialogue corpus, runs extraction → signature active. Zero file-hunting, zero corpus preparation.
/cogsig init as their first plugin command--yes skips confirmation (for scripted setup)--no-seed creates empty state for cold-start users--claude-projects PATH overrides the default ~/.claude/projects scan location~/.claude/projects/**/*.jsonl--yes)dialogue_ingest with Claude Code native formatextract --domain directing.signature-cache/ outputs/cogsig export.signature-cache/samples.json — aggregated user-directive corpussignature.json — active signature.signature-cache/signature_history.jsonl — first history entry.signature-cache/advisor_reports/*.json if advisor consultedAnthropic Claude Advisor pattern — consulted at executor inflection points (low-confidence extraction, ambiguous dimensions, conflicting governance, unexplained drift) for strategic reframe rather than parameter-tuning.
CogSig v2 enforcement layer — convert signature from inject-only to inject+act. PreToolUse hook checks every Edit/Write/MultiEdit against the active signature.json and warns or rejects per the user's selected mode.
Prepend the current signature.json to Claude's context so code suggestions can mirror the user's style (Claude reads the signature each prompt and decides how closely to follow). INJECT-CONTEXT tier — see `skills/enforce/SKILL.md` + README "Architecture: Inject + Act" for the v2 force-mechanic. Auto-fires on every UserPromptSubmit via plugin hook; also invokable manually as `/cogsig inject`.
Slash command to enable, disable, or diff the cognitive signature injection.
Pattern-review surface for pending patterns. After extraction, diff new-signature vs permanent-signature — items at instance_count ≥ 2 not already in permanent become "pending." User approves / rejects / edits via slash commands, OR Claude surfaces them inline via inject.py next-response context.
Call Opus 4.7 on cached code samples to produce a structured signature.json capturing the user's coding style.