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/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/antropos17/aegis/agents-md"><img src="https://agentmods.dev/badge/instructions/antropos17/aegis/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/antropos17/aegis/agents-md"><img src="https://agentmods.dev/badge/instructions/antropos17/aegis/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 | $0.00625 | $0.00625 |
| Opus 5.5 | $0.00250 | $0.00250 |
| Sonnet 5.5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
Aegis 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 yesterday.
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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AEGIS
AEGIS is an Electron desktop app that monitors local AI agents, with a Svelte renderer and Vitest tests.
Explicit user instructions take precedence over repository guidance. If a repository instruction blocks requested work, name its file and quote the rule.
Read for the task
- Starting or resuming work: use Current development context to identify the checkout, task and evidence.
- Code or documentation changes and reviews: read CODING_STANDARDS.md.
- Checkout isolation, source navigation, dependency setup, verification or the PR cycle: read the relevant sections of Development workflow.
- Observatory frontend work: also read its instructions; they identify the visual authority and host-integration rules.
- Identity stamping, snapshot-session or sequence-rule changes: read the runtime invariants in CODING_STANDARDS.md.
- Identity stamping, audit-chain or Windows worktree work: read the relevant history in memory-bank/ai-mistakes.md.
Permissions and boundaries
Local fixture tests and the full git cycle (branch from origin/master, commit, push, open a PR and merge) are authorised in advance. Follow the development workflow and wait for all required CI contexts before merging.
Human authorisation is required for cutting a release tag, force pushing, regenerating the lockfile, deleting a remote branch other than the one just merged, or changing anything under .github/workflows/ or .codex/config.toml. An explicit user request for that action supplies the authorisation.
Delivery and verification
When starting or resuming in a preserved checkout, resolve current process rules using policy freshness before selecting checks or installing skills. Old source stays pinned; obsolete workflow requirements do not become current authorization.
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.
- yesterday Changed · +21 lines · +238 tokens per session 52bf3b955338
- 10d ago Changed · +1 lines · +29 tokens per session fe5ae0e51150
- 19d ago Changed · -34 lines · -778 tokens per session 3de305a68e17
- 20d ago Changed fd82b237bb39
- 21d ago Changed 13b940b5d333
- 26d ago Changed 476239c8b8fe
- 28d ago Changed a64e20ce9dc6
- 29d ago Changed 5f76e2865f9a
- 1mo ago Changed 93ba1908425c
- 1mo ago First seen · 58 lines · 1,136 tokens per session scan A 3c5029b64661
Aegis AGENTS.md is an instructions file published in the GitHub repository antropos17/Aegis (159 stars, last pushed today), licensed MIT. It adds 625 tokens to every session, about $0.0025 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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.