Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/griffinwork40/agent-framework/claude-mdgit clone --depth 1 https://github.com/griffinwork40/agent-frameworkWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01237 | $0.01237 |
| Opus 5 | $0.00619 | $0.00619 |
| Sonnet 5 | $0.00247 | $0.00247 |
| Haiku 4.5 | $0.00124 | $0.00124 |
Grade A, and why
agent-framework CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
A Claude Code plugin (agent-workflow-amplifiers) containing high-leverage skills and agents that improve multi-agent orchestration, API integration, and one-shot task completion. Installed via the .claude-plugin/plugin.json manifest.
Repository Structure
.claude-plugin/
plugin.json # Plugin manifest (name, version, author, license) — version auto-synced by release-please
marketplace.json # Marketplace listing
agents/
qualify.md # Gate-keeper agent: approves/rejects proposed skills
unqualify.md # Removal agent: dry-run plan → confirmed destruction, logged to the ledger
commands/
qualify.md # /qualify slash command — dispatches the qualify agent
unqualify.md # /unqualify slash command — dispatches the unqualify agent
skills/
agentify/SKILL.md # Bootstraps sub-agent skills for each locally-installed coding agent CLI
appmap/SKILL.md # Map a web UI → create a Claude skill to automate it
automate/SKILL.md # Cron/launchd-driven headless Claude runs → Telegram summaries
contract/SKILL.md # Sub-agent I/O schema reference (loaded by orchestrator skills via /contract; also preloaded into agents via `skills:` field)
forge-friction/SKILL.md # Surface friction patterns and identify actionable skill opportunities
ground-state/SKILL.md # Pre-implementation recon wave (git + infra + memory) → 5-line ground-truth snapshot
integrate/SKILL.md # API docs → CLI wrapper + skill + tests pipeline
provideme/SKILL.md # Any coding-agent CLI → local Anthropic-compatible /v1/messages bridge
research/SKILL.md # Parallel web + local codebase research brief
resolve/SKILL.md # Resolve PR code review feedback via parallel sub-agents
ship/SKILL.md # Release pipeline: ground-state → tests → commit → push → PR (--verify adds adversarial wave)
spec/SKILL.md # Idea → structured spec
web/SKILL.md # Parallel browser automation across independent Chrome tabs
hooks/
hooks.json # Plugin hooks (currently empty)
scripts/
friction/
analyzer.py # Reads Claude Code native telemetry to surface friction patterns
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 100 lines · 1,237 tokens per session scan A a706275c1474
agent-framework CLAUDE.md is an instructions file published in the GitHub repository griffinwork40/agent-framework (23 stars, last pushed 7d ago), licensed Apache-2.0. It adds 1,237 tokens to every session, about $0.0062 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.