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/ysfaskri/archguardian/claude-mdgit clone --depth 1 https://github.com/ysfAskri/archguardianWrote 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/ysfaskri/archguardian/claude-md)<a href="https://agentmods.dev/instructions/ysfaskri/archguardian/claude-md"><img src="https://agentmods.dev/badge/instructions/ysfaskri/archguardian/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 5.1 | $0.00867 | $0.00867 |
| Opus 5 | $0.00434 | $0.00434 |
| Sonnet 5 | $0.00173 | $0.00173 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
archguardian 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 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.
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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
archguardian
Pre-commit hook and CLI that catches security issues, AI-generated code smells, naming convention violations, code duplication, architecture layer breaches, complexity metrics, dead code, IaC misconfigurations, and license compliance. Works with TypeScript, JavaScript, Python, Go, Rust, and Java.
Project structure
src/
├── cli/ Commander.js entry, 12 commands (init, check, scan, fix, learn, rules, metrics, dashboard, dismiss, summarize, diagram, sbom), output formatters (terminal, JSON, SARIF)
├── core/ Pipeline orchestrator, config loader, diff parser, suppression directives, baseline mode, workspace resolver, dependency collector, types
├── parsers/ ast-grep NAPI parser (TS/JS/Python/Go/Rust/Java) + AST utilities
├── analyzers/ Security, AI smells, conventions, duplicates, layer violations, complexity, IaC, dead code, coverage, licenses, structural rules, taint (with cross-file)
├── plugins/ Dynamic plugin loader for external analyzers
├── llm/ LLM client (OpenAI, Anthropic, Gemini), prompt builder, file-based cache
├── fixes/ Auto-fix engine (remove unused imports, rename conventions)
├── metrics/ Run history tracker (.archguard/metrics.json)
├── hooks/ Git hook installer (direct + Husky)
├── ci/ GitHub annotator + PR review bot + PR summary commenter
└── utils/ Git operations, logging, perf timing
Build & test
npm run build # tsup → dist/
npm test # vitest (273 tests)
npm run typecheck # tsc --noEmit
Key conventions
- ESM-only (
"type": "module"in package.json), all imports use.jsextensions - Node >= 18 required
- AST parsing via ast-grep NAPI (native tree-sitter bindings, not WASM)
- Tests in
tests/unit/,tests/integration/,tests/e2e/using vitest - Config file:
.archguard.ymlvalidated with Zod schemas - Pipeline: analyzers run in parallel with 5s timeout each, findings are deduplicated, then suppressed, then optionally enhanced by LLM
- Monorepo support via
workspacesconfig with glob-based overrides
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 · 60 lines · 867 tokens per session scan A ffbbc7a72541
archguardian CLAUDE.md is an instructions file published in the GitHub repository ysfAskri/archguardian (4 stars, last pushed 6mo ago), licensed MIT. It adds 867 tokens to every session, about $0.0043 per session on Opus 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
truecourse CLAUDE.md
Claude Code instructions for truecourse-ai/truecourse, covering truecourse — claude instructions, key files to keep updated, project layout, development commands and storage.
truecourse AGENTS.md
AGENTS.md instructions for truecourse-ai/truecourse, covering truecourse — codex instructions, key files to keep updated, project layout, development commands and rules.
PhpCodeArcheology CLAUDE.md
Instructions for PhpCodeArcheology/PhpCodeArcheology, covering claude.md — phpcodearcheology, project overview, language, tech stack and project structure.
drift copilot-instructions.md
Instructions for mick-gsk/drift, covering drift — verbindliche arbeitsgrundlage für alle agenten, primärmodus bei prompt-engineering, zuerst das richtige primitive wählen, nicht verhandelbare schärferegeln and mindestvertrag für jeden guten prompt.
drift drift-push-gates.instructions.md
Nutze diese Instruction, wenn ein Commit, ein Push oder eine Release-Vorbereitung im Drift-Repo ansteht. Sie ist die autoritative Gate-Quelle fuer Pre-Push-Anforderungen, Bypaesse und lokale CI-Pflichten.
drift drift-quality-workflow.instructions.md
Nutze diese Instruction bei nicht-trivialen Aenderungen, Reviews oder Fix-Loops im Drift-Repo. Fokus: adversarialer Gegenreview, iterativer Fix-Loop, expliziter Freigabestatus und Human-in-the-Loop vor Merge.