agentmods.dev

agent-reliability-kit AGENTS.md

Project instructions for agent-reliability-kit, a TypeScript command-line project that checks coding-agent work. They define development commands, safety rules, and the required contents of reports.

In plain words
What is it for?
Use them to build, type-check, test, lint, and smoke-test the project, and to produce concise reports with severity, file, reason, and next action.
Why use it?
They keep changes small and verifiable while preventing secrets, private logs, and unrequested publishing actions from entering the project.

Instructions file for CodexOpenCode

2 1mo ago A scan 211 tokens original MIT
View the source file aolingge/agent-reliability-kit
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/aolingge/agent-reliability-kit/agents-md
Clone the repo
git clone --depth 1 https://github.com/aolingge/agent-reliability-kit

Made for: Codex, OpenCode.

Per session 211 This file is loaded in full into every session.
When invoked 211 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 $0.00211 $0.00211
Opus 5 $0.00105 $0.00105
Sonnet 5 $0.00042 $0.00042
Haiku 4.5 $0.00021 $0.00021

Measured yesterday against content hash 70caea910ff5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-reliability-kit 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.

AGENTS.md · 28 lines

What it actually says

Agent Instructions

This repository is a public TypeScript CLI project. Keep changes small, testable, and safe to publish.

Commands

  • Install: npm install
  • Build: npm run build
  • Typecheck: npm run typecheck
  • Test: npm test
  • Lint: npm run lint
  • Full verification: npm run check
  • Smoke test after build: npm run smoke

Safety

  • Never commit secrets, tokens, cookies, browser profiles, private paths, or raw private logs.
  • Fixtures may contain fake token-looking strings only when they are obviously synthetic and used to test redaction.
  • Do not publish to npm, create GitHub releases, or push remote branches unless the user explicitly asks.
  • Do not enable OMX project configuration in this workspace.

Style

  • Code and public docs are written in English.
  • Keep CLI output concise, actionable, and friendly for GitHub Actions logs.
  • Reports must include severity, file path, reason, and next action.
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. yesterday First seen · 28 lines · 211 tokens per session scan A 70caea910ff5

Subscribe to this mod's changes

agent-reliability-kit AGENTS.md is an instructions file published in the GitHub repository aolingge/agent-reliability-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 211 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 2026-08-31.

Code reviewDevOps and cloudTestingai-agentciclaude-codeclicodexcoding-agents
Related

Other instructions, from other repositories

agents-md-doctor AGENTS.md

Instructions for ItsHege/agents-md-doctor, covering agents.md doctor public agent instructions, scope of this file, project goal, current baseline and working rules.

ItsHege/agents-md-doctor · 1,124 tokens

std-env AGENTS.md

Instructions for unjs/std-env, covering agents, project overview, maintenance, scripts and source structure.

unjs/std-env · 2,188 tokens

ontology-atlas AGENTS.md

Instructions for wlsdks/ontology-atlas, covering agents.md — ontology-atlas, product and non-negotiable architecture, start here, structure and routes and operating gates and skills.

wlsdks/ontology-atlas · 2,685 tokens

ephemeral-sandbox CLAUDE.md

Instructions for Ephemeral-AI-Lab/ephemeral-sandbox, covering claude.md, project, engineering practice (required), build & test and sandbox tools.

Ephemeral-AI-Lab/ephemeral-sandbox · 1,203 tokens

coral CLAUDE.md

Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).

cdknorow/coral · 1,898 tokens

pixir CLAUDE.md

Instructions for Ranvier-Technologies/pixir, covering pixir harness - legacy agent guide, current map and commands.

Ranvier-Technologies/pixir · 246 tokens