Borrowing it
Nothing to install: this file belongs to raccioly/websec-validator. 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/raccioly/websec-validator/main/AGENTS.mdgit clone --depth 1 https://github.com/raccioly/websec-validatorWrote 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/raccioly/websec-validator/agents-md)<a href="https://agentmods.dev/instructions/raccioly/websec-validator/agents-md"><img src="https://agentmods.dev/badge/instructions/raccioly/websec-validator/agents-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/raccioly/websec-validator/agents-md"><img src="https://agentmods.dev/badge/instructions/raccioly/websec-validator/agents-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 | $0.02781 | $0.02781 |
| Opus 5.5 | $0.01112 | $0.01112 |
| Sonnet 5.5 | $0.00556 | $0.00556 |
| Haiku 4.5 | $0.00278 | $0.00278 |
Grade A, and why
websec-validator AGENTS.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 16d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This project follows Canonical-Driven Development (CDD).
Read canonical docs before making changes. Log drift when deviating.
Project Overview
websec-validator is a local-first security-recon CLI that briefs an AI coding agent. It maps a repo's
attack surface, de-duplicates the static scanners it finds, stages a tailored probe library, and emits
an AGENT-BRIEFING.md — code in, artifacts out; no LLM, no server, no running app for the core
pass. Pure-Python, stdlib only, zero runtime dependencies; it shells out to external scanners
(Trivy/Gitleaks/Semgrep/Checkov; Prowler is detected but not executed) and OWASP Noir when present. The package lives in
src/websec_validator/; the architecture is in docs-canonical/ARCHITECTURE.md.
Project Documentation (CDD)
- Canonical docs (design intent, review-gated):
docs-canonical/—ARCHITECTURE.md,SECURITY.md,TEST-SPEC.md,ENVIRONMENT.md - User documentation (install, guides, reference — start at the hub):
docs/README.md. The reference pages are bound to the code bytests/test_docs_reference.py: a new subcommand, flag, language profile or doc page fails CI untildocs/reference/cli.md,docs/reference/languages.mdand the hub are updated. Guides show<reviewed-commit-sha>placeholders, never release pins. - Long-form methodology (the why behind every check):
docs/METHODOLOGY.md - Proof protocol:
corpus/PROOF-PROTOCOL.md - Drift tracking:
DRIFT-LOG.md· Change tracking:CHANGELOG.md - Spec Kit constitution:
.specify/memory/constitution.md
Build & Dev Commands
| Command | Purpose |
|---|---|
pipx install --editable . |
Install the CLI from source (or pip install -e . in a 3.11+ venv) |
python3 -m unittest discover -s tests |
Run the suite (stdlib only, no public network; one opt-in lifecycle skipped) |
python3 scripts/build-brief.py --check |
Verify the committed HTML/PDF/renderer binding offline; rebuild and review all eight pages after source edits |
websec run ./target |
Full pipeline → FACTS.json + AGENT-BRIEFING.md + probes/ |
websec doctor ./target |
Show which optional scanners are installed |
websec gate |
Fast scoped pass/fail on the files you just changed (agent-loop check) |
websec attest |
Project a run into an audit-evidence table (gaps first; no verdict) |
websec proof |
Score recon coverage vs the vuln-app corpus (needs network on first clone) |
docguard guard |
Validate documentation against the code (CDD) |
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.
- 16d ago Changed · +16 lines · +313 tokens per session 44eb9f5ce830
- 17d ago Changed · +9 lines · +171 tokens per session 3d3001e0701a
- 26d ago Changed · +7 lines · +140 tokens per session 93b7740d15d4
- 27d ago Changed 6ec9574c25f5
- 1mo ago Changed 09811529ad3a
- 1mo ago Changed a1d98f8bf2f8
- 1mo ago Changed · +5 lines · +95 tokens per session d08190fe3072
- 1mo ago Changed · +2 lines · +54 tokens per session 76762c12ddda
- 1mo ago Changed · +20 lines · +460 tokens per session 701ef630d80c
- 1mo ago First seen · 115 lines · 1,548 tokens per session scan A 8b850bb83d66
websec-validator AGENTS.md is an instructions file published in the GitHub repository raccioly/websec-validator (2 stars, last pushed today), licensed MIT. It adds 2,781 tokens to every session, about $0.0111 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 2026-08-31.
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.