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/mhw888888/aegisloop/agents-mdgit clone --depth 1 https://github.com/MHW888888/aegisloopWrote 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/mhw888888/aegisloop/agents-md)<a href="https://agentmods.dev/instructions/mhw888888/aegisloop/agents-md"><img src="https://agentmods.dev/badge/instructions/mhw888888/aegisloop/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 | $0.00224 | $0.00224 |
| Opus 5 | $0.00112 | $0.00112 |
| Sonnet 5 | $0.00045 | $0.00045 |
| Haiku 4.5 | $0.00022 | $0.00022 |
Grade A, and why
aegisloop 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 4d 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.
What it actually says
AegisLoop Development Rules
Scope
- Keep changes limited to the requested release objective.
- Preserve Chat Mode as the default and require explicit arming before dispatch.
- Do not weaken API token, Origin, leader lease, turn token, pending-result, capsule, or policy gates.
Safety
- Never commit
config.json, tokens,state.json, logs, jobs, runs, local paths, or Codex session ids. - Do not automatically retry an execution after it may have produced file, command, or MCP side effects.
- Treat an interrupted job as
recovery_requiredunless completion can be proven from persisted state. - Keep legacy execution only as a capability-based compatibility fallback selected before a job starts.
Verification
- Add a regression test for each bug fix.
- Run
npm run checkbefore publishing. - Run
npm run doctorwithout exposing configured secrets. - Keep package, extension manifest, and content-script versions aligned.
Publishing
- Prefer a branch and pull request over direct writes to
main. - Do not merge while required checks are failing.
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.
- 4d ago First seen · 27 lines · 224 tokens per session scan A 4a9530fe0484
aegisloop AGENTS.md is an instructions file published in the GitHub repository MHW888888/aegisloop (19 stars, last pushed 2d ago), licensed MIT. It adds 224 tokens to every session, about $0.0011 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
chat-on-steroids CLAUDE.md
Claude Code instructions for totec448-spec/chat-on-steroids: Read and follow AGENTS.md before changing this repository.
AI-MarkDone copilot-instructions.md
Instructions for zhaoliangbin42/AI-MarkDone, covering ai copy enhance - ai coding agent instructions, project overview, architecture patterns, adapter pattern for multi-platform support and shadow dom isolation.
AI-MarkDone AGENTS.md
Instructions for zhaoliangbin42/AI-MarkDone, covering ai-markdone engineering guide, project facts, read order, common commands and non-negotiables.
agent-inbox AGENTS.md
Instructions for OGZamasu/agent-inbox, covering connecting an agent, claude code, chatgpt — custom gpt with actions, mcp clients and anything else.
multi-ai-panel AGENTS.md
AGENTS.md instructions for xiaojiou176-open/multi-ai-panel, covering agents, public surface rules, current visibility truth, protected paths and no-code-loss and destructive action discipline.
multi-ai-panel CLAUDE.md
Claude Code instructions for xiaojiou176-open/multi-ai-panel, covering claude, repository intent, current host truth, public repository rules and minimal verification.