Borrowing it
Nothing to install: this file belongs to justi/claude-code-project-boundary. 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/justi/claude-code-project-boundary/main/CLAUDE.mdgit clone --depth 1 https://github.com/justi/claude-code-project-boundaryWrote 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/justi/claude-code-project-boundary/claude-md)<a href="https://agentmods.dev/instructions/justi/claude-code-project-boundary/claude-md"><img src="https://agentmods.dev/badge/instructions/justi/claude-code-project-boundary/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/justi/claude-code-project-boundary/claude-md"><img src="https://agentmods.dev/badge/instructions/justi/claude-code-project-boundary/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 | $0.00483 | $0.00483 |
| Opus 5.5 | $0.00193 | $0.00193 |
| Sonnet 5.5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
claude-code-project-boundary 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
project-boundary — plugin development notes
Rules for anyone (Claude included) editing this plugin.
hooks/session_hint.md — context-budget discipline
The contents of session_hint.md are cat-ed by the SessionStart hook and prepended to every session's context window for every user of this plugin. Every byte costs the user tokens forever.
Rules when editing the hint:
- Hard budget: 800 bytes of stdout. Enforced by
tests/test_session_hint.sh. - One short paragraph per quirk. Prefer the "avoid X, use Y" pattern as a single line; a brief multi-line example (e.g. a heredoc showing the ONE supported form) is allowed when it saves Claude multiple tool calls. If you add an example, keep it minimal and still within the 800-byte budget.
- Only add a quirk if Claude measurably wastes tool calls without it.
- Remove obsolete hints as soon as the underlying guard behavior changes.
- If you hit the budget, delete an old hint before adding a new one — never bump the budget casually.
The test measures wc -c < session_hint.md directly.
hooks/allowlist.conf — path-allowlist discipline
Every entry is an escape hatch from the project boundary. See the warning at the top of allowlist.conf for the bypass risks. Keep entries narrow, purpose-specific, and comment the reason each one exists.
Security-bypass TDD flow
When closing a new bypass category in hooks/guard.sh, follow this flow strictly, one bypass at a time:
- Reproducer first — add a failing test to
tests/test_bypass_reproducers.sh(expected: BLOCKED, exit 2). - Confirm bypass exists — run the suite; new test must FAIL. If it passes immediately, the bypass doesn't exist — stop.
- Patch — modify
hooks/guard.sh. - Regression — full
tests/test_guard.shmust be green. - Positive case — if the patch is broad, add a test of a legal use that must still PASS, so we don't over-block real workflows.
Don't batch several bypasses into one commit — regression coverage gets muddy.
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 First seen · 34 lines · 483 tokens per session scan A 28ea2d92e756
claude-code-project-boundary CLAUDE.md is an instructions file published in the GitHub repository justi/claude-code-project-boundary (90 stars, last pushed 2mo ago), licensed MIT. It adds 483 tokens to every session, about $0.0019 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.