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/0xrafasec/ai-workflow/claude-mdgit clone --depth 1 https://github.com/0xrafasec/ai-workflowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/0xrafasec/ai-workflow/claude-md)<a href="https://agentmods.dev/instructions/0xrafasec/ai-workflow/claude-md"><img src="https://agentmods.dev/badge/instructions/0xrafasec/ai-workflow/claude-md.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.01179 | $0.01179 |
| Opus 5 | $0.00589 | $0.00589 |
| Sonnet 5 | $0.00236 | $0.00236 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade B, and why
ai-workflow CLAUDE.md scanned grade B with 1 finding 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 5d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Edit the source in this repo, never the symlink in `~/.claude/`.** Edits to `~/.claude/<thing>` will either be lost on the next `install.sh` run or break the symlink. If you find yourself reading from `~/.claude/...` How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ai-workflow — Project-Specific Instructions
These rules apply only when working inside the ai-workflow repo. The global Claude defaults live at dotfiles/CLAUDE.md (symlinked to ~/.claude/CLAUDE.md by install.sh) and apply to every project.
Repo layout
This repo is the source of truth for everything installed under ~/.claude/:
dotfiles/CLAUDE.md— global defaults, symlinked to~/.claude/CLAUDE.mdCLAUDE.md(this file) — project-specific rules, loaded only whencwdis this reposkills/<name>/SKILL.md— slash-command skills, symlinked into~/.claude/skills/agents/,commands/,reviews/,settings.json— symlinked similarly viainstall.shadapters/codex/,adapters/cursor/— compile the skills + global CLAUDE.md into formats those tools understandextras/— opt-in personal skills, only installed via./install.sh --extra
Editing rules
- Edit the source in this repo, never the symlink in
~/.claude/. Edits to~/.claude/<thing>will either be lost on the nextinstall.shrun or break the symlink. If you find yourself reading from~/.claude/...to make a change, stop and re-open the matching file in this repo. - Re-run
install.shafter adding, removing, or renaming any skill, agent, or command. Editing existing files in place is fine — symlinks already point at them. Only the directory shape changes need a re-link.
Docs are part of the change — never ship a behavior change without doc updates
Any change to a skill, workflow, convention, or installer must update the relevant docs in the same change. Docs are not a follow-up. They are part of the change.
When you change something in this list (left), update the docs on the right in the same commit/PR:
| Change | Update |
|---|---|
| Skill behavior, args, or removal/rename | skills/<name>/SKILL.md (the source), docs/REFERENCE.md skill section, README.md Skills table + tree, CHANGELOG.md |
| Workflow convention (trunk rules, commit style, etc.) | dotfiles/CLAUDE.md, docs/WORKFLOW.md, docs/TRUNK_BASED_WORKFLOW.md, CHANGELOG.md |
| Adding/removing a skill | install.sh, uninstall.sh, README.md "Available skills" list, dotfiles/CLAUDE.md "Toolkit" section, adapters (codex/cursor), CHANGELOG.md |
| Installer or symlink layout | install.sh, uninstall.sh, adapters, README.md install section, docs/REFERENCE.md layout section, CHANGELOG.md |
| New or repurposed top-level convention file | README.md repo-tree section, docs/REFERENCE.md layout section |
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.
- 5d ago First seen · 61 lines · 1,179 tokens per session scan B 1c61397e646a
ai-workflow CLAUDE.md is an instructions file published in the GitHub repository 0xrafasec/ai-workflow (9 stars, last pushed 3d ago), licensed MIT. It adds 1,179 tokens to every session, about $0.0059 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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.
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).