claude

instructions

Keep the agent instruction system small and true — its rules (instructions-maintenance, rules-change), the instructions-audit sweep + auditor agent, and the caps / meta-lint size and structure checks.

2 on GitHubby optimiziramsiv0.2.0MITupdated yesterdayworkflow
/

Plugin instructions from marketplace optimiziramsi in optimiziramsi/skills. Commands read from the repo's manifest — yesterday.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (3)

  • instructions-audit

    De-rot the agent instruction system — after many sessions of accretion, keep it SMALL, TRUE, and NON-DUPLICATED. Sweeps for broken pointers, dead/duplicate rules, truth-vs-reality drift, cap breaches, and enforcement drift; applies safe fixes (T2) directly and batches risky ones (T3) into one propos

  • instructions-maintenance

    The constitution of the agent instruction system — the rules for how CLAUDE.md, .claude/ (skills, rules, hooks, settings, agents), and .agent/ evolve. Load this BEFORE creating or modifying any instruction file, when adding a skill/rule/hook/agent, changing a convention, or capturing a lesson. Owns

  • rules-change

    The sanctioned way to make a T3 change to the instruction system — add/remove a rule, change a cap, or change any hook/skill/agent/settings behavior. Use ONLY on an explicit user request or approval (including approving a retro/audit proposal, or granting a one-time exception). Never invoke as a sid

Slash commands (3)

  • /instructions:instructions-audit

    De-rot the instruction system — pointers, liveness, truth-vs-reality, duplicates, caps, enforcement; T2 applied, T3 proposed (runs the instructions-audit skill)

  • /instructions:instructions-maintenance

    Load the instruction-system constitution before changing CLAUDE.md / .claude / .agent (runs the instructions-maintenance skill)

  • /instructions:rules-change

    The sanctioned way to change a rule/cap/enforcement — explicit approval, coherence check, re-test, changelog (runs the rules-change skill)

Subagents (1)

  • instructions-auditor

    Read-only auditor for a repo's agent-instruction system. Used by /instructions-audit (or directly) to sweep CLAUDE.md, .claude/**, and .agent/** for broken pointers, dead/duplicate rules, contradictions with reality, cap breaches, and enforcement drift. Returns a severity-ranked findings list with f

Hooks (3)

  • Stop

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/caps.py"

  • Stop

    python3 "${CLAUDE_PLUGIN_ROOT}/bin/meta-lint" --stop

  • Stop

    python3 "${CLAUDE_PLUGIN_ROOT}/bin/meta-lint" --end-note || echo '{"systemMessage":"⚠️ meta-lint DISARMED — engine failed to run; instruction-system checks did NOT run this session."}'

View source on GitHub

More from optimiziramsi/skills

All 21 plugins →

review

claude

Structured review — the review skill (P0/HIGH/MED/LOW → .agent/reviews/) plus semantic-bug, spec, doc-drift, multi-tenant isolation and wireframe reviewer agents.

1 skill · 1 command · 5 agents

2

runners

claude

Unattended background work — looper / grind / collab prepare jobs that the shipped loop and grind runners execute as headless claude sessions, confined when run in a worktree.

3 skills · 3 commands · hooks

2

session

claude

Session continuity — handoff (next-session notes, ≤4k), continue, session-summary, and a SessionStart state snapshot.

3 skills · 3 commands · hooks

2

todo

claude

The .todo parking lot — triage-todo, feedback and scope-cut, plus a guard that keeps .todo the user's (arm with "ALLOW TODO").

3 skills · 3 commands · hooks

2

lessons

claude

Learn once, keep it — retro harvests a session's learnings, lessons curates them in .agent/lessons/, and the lesson-scout agent finds prior art before you re-debug.

2 skills · 2 commands · 1 agent

2

patterns

claude

Per-topic pattern registry under .agent/patterns/ — manage-patterns, pattern-compliance / pattern-verifier agents, and hooks that gate edits governed only by non-blessed patterns.

1 skill · 1 command · 2 agents · hooks

2

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

backend-development

claudecodex

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

beads

claudecodex

AI-supervised issue tracker for coding workflows

1 skill · 1 agent · hooks

gastownhall/beads 28,698

minimax-skills

claude

MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows

18 skills

MiniMax-AI/skills 13,828

worktrunk

claudecodex

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.

2 skills · hooks

max-sixty/worktrunk 12,481

gsd-core

claude

GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.

72 skills · 72 commands · 64 agents · hooks

open-gsd/gsd-core 11,494

Maintain instructions?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins21 plugins