Borrowing it
Nothing to install: this file belongs to chan4lk/specclaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chan4lk/specclaw/main/CLAUDE.mdgit clone --depth 1 https://github.com/chan4lk/specclawWrote 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/chan4lk/specclaw/claude-md)<a href="https://agentmods.dev/instructions/chan4lk/specclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/chan4lk/specclaw/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/chan4lk/specclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/chan4lk/specclaw/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01026 | $0.01026 |
| Opus 5.5 | $0.00410 | $0.00410 |
| Sonnet 5.5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
specclaw 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 1mo 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the assistant for the specclaw project.
Working directory: this is a git checkout of the specclaw repo (base branch main). Commands run from here. One remote exists:
origin = chan4lk/specclaw (branches are pushed there and PRs are merged there). There is no upstream remote in this checkout. Confirm with git remote -v rather than trusting this line.
You can use Bash freely (auto permission mode). Useful binaries on PATH: git, gh (GitHub CLI), node/npm, bun, python.
Git workflow
- Always
git pull --ff-only origin mainbefore starting work. - Make changes on a feature branch — never commit directly to
main. Branch names:claude/<short-task>or<operator-handle>/<topic>. - Stage and commit small focused units. Use clear commit messages with the why, not just the what.
- Push the branch (
git push -u origin <branch>). Authentication is already wired viaGIT_ASKPASSorGIT_SSH_COMMAND— no token prompts. - Open a pull request with
gh pr create --repo chan4lk/specclaw --base main --head <branch> --title "..." --body "...". Report the PR URL (in Discord viamcp__mcd__replywhen running under the Discord channel, otherwise in the terminal reply). Always name--repoexplicitly. If a second remote is ever added, a baregh pr createmay resolve to it and open a cross-fork PR against the wrong repo. PRs are merged onchan4lk/specclaw. - For small fixes, request review in the PR body or
@mentionthe operator.
Version bump rule
Always bump the plugin version before opening a PR. This applies to every PR — features, fixes, and chores alike.
Version files to bump (patch increment X.Y.Z → X.Y.Z+1):
plugins/specclaw/.claude-plugin/plugin.json—"version"field.claude-plugin/marketplace.json—"version"field inside the"plugins"array entry for"specclaw"
Both files must stay in sync. Commit the bump as a separate commit (chore: bump version to X.Y.Z) before or as part of the PR branch. specclaw-pr will auto-bump via ensure_version_bumped() if plugin.version_files is configured, but do it manually when working outside the specclaw lifecycle.
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.
- 1mo ago Changed · +2 lines · +47 tokens per session 4fec8a8fcb8b
- 1mo ago Changed · +2 lines · +138 tokens per session c93656559061
- 1mo ago First seen · 45 lines · 841 tokens per session scan A f99e23b93a15
specclaw CLAUDE.md is an instructions file published in the GitHub repository chan4lk/specclaw (13 stars, last pushed 8d ago), licensed MIT. It adds 1,026 tokens to every session, about $0.0041 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.