Borrowing it
Nothing to install: this file belongs to antropos17/Aegis. 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/antropos17/Aegis/master/CLAUDE.mdgit clone --depth 1 https://github.com/antropos17/AegisWrote 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/antropos17/aegis/claude-md)<a href="https://agentmods.dev/instructions/antropos17/aegis/claude-md"><img src="https://agentmods.dev/badge/instructions/antropos17/aegis/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 | $0.02463 | $0.02463 |
| Opus 5 | $0.01231 | $0.01231 |
| Sonnet 5 | $0.00493 | $0.00493 |
| Haiku 4.5 | $0.00246 | $0.00246 |
Grade C, and why
Aegis CLAUDE.md scanned grade C with 1 finding 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 6d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
only the project-level settings.json `deny` (rm -rf, git push --force, .env reads) is a hard floor. How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AEGIS — Independent AI Oversight Layer
Electron 43 + Svelte 5 (runes) + Vite 7. Privacy-first AI agent monitor.
Version is not quoted here — it goes stale the moment it is bumped:
node -p "require('./package.json').version"
Landing: aegisprotect.vercel.app | Demo: aegis-demo-ten.vercel.app
Commands
npm run build:renderer # Vite build (MUST pass before commit) npm run lint # ESLint npm run format # Prettier npm test # Vitest — the suite prints its own counts; do not copy them here npm run verify:gate # Injection proof: 4 mutants (witness gate + birth-time freshness) must go red npm run verify:seq-gate # Injection proof: 4 sequence-engine mutants (order, expiry, group key, caps) must go red npm run counts:check # Every counted fact derived from the tree; a stale declaration is red npm run dist # Electron-builder NSIS installer
Verification — three different counts, do not merge them
5 required status contexts are what GitHub enforces on master. Proven with
gh api repos/antropos17/Aegis/branches/master/protection --jq '.required_status_checks'
→ contexts [build, lint, svelte-check, test, audit], strict: true (branch must be up to
date before merge). No rulesets add more: /rulesets and /rules/branches/master return [].
A context is a JOB, not a command — lint and svelte-check run two commands each.
10 verification commands live inside those 5 jobs (.github/workflows/ci.yml):
| required context | commands the job runs, after npm ci |
|---|---|
| build | npm run build:renderer |
| lint | npm run format:check, then npm run lint |
| svelte-check | npm run typecheck, then npm run typecheck:svelte |
| test | npm run test:coverage, npm run verify:gate, npm run verify:seq-gate, then npm run counts:check |
| audit | npm audit --audit-level=high --omit=dev |
format:check is a STEP of lint, and verify:gate, verify:seq-gate and counts:check are
STEPS of test — none is a job, and none is a context of its own.
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.
- 6d ago First seen · 115 lines · 2,463 tokens per session scan C f9539adf4b02
Aegis CLAUDE.md is an instructions file published in the GitHub repository antropos17/Aegis (145 stars, last pushed 12d ago), licensed MIT. It adds 2,463 tokens to every session, about $0.0123 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.