Borrowing it
Nothing to install: this file belongs to agamm/claude-code-owasp. 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/agamm/claude-code-owasp/main/CLAUDE.mdgit clone --depth 1 https://github.com/agamm/claude-code-owaspWrote 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/agamm/claude-code-owasp/claude-md)<a href="https://agentmods.dev/instructions/agamm/claude-code-owasp/claude-md"><img src="https://agentmods.dev/badge/instructions/agamm/claude-code-owasp/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/agamm/claude-code-owasp/claude-md"><img src="https://agentmods.dev/badge/instructions/agamm/claude-code-owasp/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 | $0.00314 | $0.00314 |
| Opus 5.5 | $0.00126 | $0.00126 |
| Sonnet 5.5 | $0.00063 | $0.00063 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
claude-code-owasp 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 20d 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.
What it actually says
claude-code-owasp
Opening a pull request
Run the eval suite before opening any PR, and put the results in the PR description.
for m in sonnet opus; do
claude plugin eval . --model $m -j 4 --no-publish --json /tmp/eval-$m.json
done
- Run evals on Sonnet and Opus only. Don't run them on Haiku or other small models: the skill
isn't targeted at them, and their failures are noise in the results. Each case pins
model: sonnet, so a run without--modelalso stays on Sonnet. - Each run makes real model calls billed to the account, about $2-3 per model.
- In the description, add a table with one row per case and a "with / without" score per model,
taken from each case's
aggregates(score,scoreWithout) in the JSON. - Say which commit the numbers came from. If a later commit changes
SKILL.mdor its frontmatter, run the suite again. - Name any case that scores lower with the skill than without it, and why. Don't hide a regression.
evals/results/is gitignored. Don't commit it.- After editing any regex grader, run
node scripts/test-graders.mjs(free, no model calls) and add a pass and a fail example for the new behavior.
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.
- 20d ago First seen · 25 lines · 314 tokens per session scan A 5d2d5c42a35a
claude-code-owasp CLAUDE.md is an instructions file published in the GitHub repository agamm/claude-code-owasp (378 stars, last pushed 21d ago), licensed MIT. It adds 314 tokens to every session, about $0.0013 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 2026-09-26.
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
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).