aegisloop AGENTS.md

aegisloop AGENTS.md is an instructions file for Codex, OpenCode from MHW888888/aegisloop. It costs 224 tokens per session, scanned A, original, MIT.

Development instructions for AegisLoop, including limits on changes, safety checks, testing, and publishing. They describe how the project handles jobs that run commands or other actions.

In plain words
What is it for?
Use it when fixing bugs, adding features, running checks, handling interrupted jobs, or preparing a release of AegisLoop.
Why use it?
They help prevent unsafe retries, accidental exposure of secrets, weakened security checks, and publishing code that has not passed verification.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/mhw888888/aegisloop/agents-md
Clone the repo
git clone --depth 1 https://github.com/MHW888888/aegisloop

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for aegisloop AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mhw888888/aegisloop/agents-md.svg)](https://agentmods.dev/instructions/mhw888888/aegisloop/agents-md)
Your own site
<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>
Per session 224 This file is loaded in full into every session.
When invoked 224 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash 4a9530fe0484, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

AGENTS.md · 27 lines

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_required unless 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 check before publishing.
  • Run npm run doctor without 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.
Changes

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.

  1. 4d ago First seen · 27 lines · 224 tokens per session scan A 4a9530fe0484

Subscribe to this mod's changes

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.