Aegis is a method pack that guides coding agents to inspect a project's baseline, make bounded changes, and verify their work with fresh evidence. It is for people using coding-agent hosts who want fewer unverified changes and less unnecessary process. The catalogue add-ons implement this method through skills, instructions, commands, a hook, and a plugin.
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/ganyuanran/aegis/agents-mdgit clone --depth 1 https://github.com/GanyuanRan/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/ganyuanran/aegis/agents-md)<a href="https://agentmods.dev/instructions/ganyuanran/aegis/agents-md"><img src="https://agentmods.dev/badge/instructions/ganyuanran/aegis/agents-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 | $0.01235 | $0.01235 |
| Opus 5 | $0.00617 | $0.00617 |
| Sonnet 5 | $0.00247 | $0.00247 |
| Haiku 4.5 | $0.00123 | $0.00123 |
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 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aegis Repository Agent Guide
Status: Approved
1. Purpose
This file is the public repository guide for AI coding agents working in the
Aegis repository.
It defines:
- what this repository is and is not
- which authority docs to read before changing behavior
- how to keep changes small, verifiable, and public-safe
- which boundaries must not drift while improving Aegis
It does not replace:
docs/current/README.mdfor the current authority map- approved ADRs in
docs/adr/ - task-specific baseline docs in
docs/current/ - installed Aegis skills and workflows
- host-specific installation docs such as
docs/README.codex.md,docs/README.opencode.md,docs/README.claude-code.md,docs/README.codebuddy.md,docs/README.deepseek-tui.md, anddocs/README.trae.md
2. Authority Order
When instructions conflict, use this order:
- The user's current explicit instruction
- this root
AGENTS.md docs/current/README.md- approved ADRs in
docs/adr/ - task-specific approved docs in
docs/current/ - host-specific docs and tests
- installed Aegis skills and workflow guidance
If the authority source is unclear, state the gap and choose the smallest verifiable path.
3. Baseline Read-Set
For non-trivial work, read these first:
docs/current/README.mddocs/adr/ADR-0001-aegis-method-pack-is-not-runtime-core.md- the smallest task-relevant
docs/current/*.md
Add these when relevant:
- prompt hygiene / context injection:
docs/current/AEGIS_PROMPT_HYGIENE_AND_INJECTION_BOUNDARY.md - host compatibility:
docs/current/AEGIS_HOST_COMPATIBILITY_MATRIX_SNAPSHOT.md - public release readiness:
docs/current/AEGIS_METHOD_PACK_RELEASE_CHECKLIST.md - Claude Code-specific work:
CLAUDE.mdanddocs/README.claude-code.md
4. Repository Positioning
The current product boundary is:
Aegis Method Pack (runtime-ready)
This repository owns:
- skills
- initial instructions
- workflow discipline
- host-installable method-pack distribution
- runtime-ready drafts, hints, and projections
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 · 185 lines · 1,235 tokens per session scan A 892cb64cdc86
Aegis AGENTS.md is an instructions file published in the GitHub repository GanyuanRan/Aegis (1,167 stars, last pushed yesterday), licensed MIT. It adds 1,235 tokens to every session, about $0.0062 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 2026-08-30.
Other instructions, from other repositories
crystal CLAUDE.md
Instructions for stravu/crystal, covering crystal - multi-session claude code manager, project overview, references, implementation status: ✅ complete and ✅ implemented features.
easy-cheese python.instructions.md
Instructions for paulnsorensen/easy-cheese, covering hard rules, what to flag and what not to flag.
plan-forge database.instructions.md
Database patterns for .NET — Dapper/EF Core, parameterized queries, migration strategy.
claude-bridge AGENTS.md
Instructions for kadaba/claude-bridge, covering agents.md — using claude-bridge from any ai coding cli, two independent channels, 1. coordination (the conversation), 2. file transfer (the bytes) — same for every tool and workflows.
AmbyKit CLAUDE.md
Claude Code instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.
sugar AGENTS.md
AGENTS.md instructions for roboticforce/sugar, covering sugar - agents.md, git branching rules (strict), always create branches from develop, after work is complete and then create pr targeting develop.