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/mikiships/agentmd/agents-mdgit clone --depth 1 https://github.com/mikiships/agentmdWhat 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 | $0.00642 | $0.00642 |
| Opus 5 | $0.00321 | $0.00321 |
| Sonnet 5 | $0.00128 | $0.00128 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
agentmd 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 2d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Agent context for OpenAI Codex. This file is read automatically by the Codex sandbox at session start.
Project Overview
Primary languages: Python Package managers: pip CI: GitHub Actions
Build, Test, and Lint Commands
Install dependencies:
pip install -e '.[dev]'
Run tests:
python3 -m pytest tests/ -x
Lint / format:
ruff check . && ruff format --check .
Directory Structure
Top-level directories: .github, agentmd, tests
Test roots: tests
Most-changed directories: agentmd, tests, README.md, pyproject.toml, progress-log.md
Sandbox Awareness
The Codex sandbox has network access disabled by default during code execution.
- Do not make HTTP requests in tests — mock all external calls.
- Do not rely on system-installed tools; prefer project-local binaries (
./node_modules/.bin/, virtualenv, etc.). - The sandbox resets between sessions — do not rely on persistent state outside the repo.
- Python dependencies: install into a virtualenv. The sandbox may not have all packages pre-installed.
Conventions Inferred from Codebase
Commit prefix style: feat, fix, chore, docs, feat(d3) (follow this pattern)
Common file extensions: .pyc, .py, .md, .toml, .yml
- Python: use type hints on all public functions
- Python: snake_case for functions/variables, PascalCase for classes
- Tests: files named
test_*.py, functions namedtest_*
apply_patch Usage
When modifying files, prefer apply_patch over full-file writes for surgical changes:
- Keep patches small and focused on the minimal diff.
- After applying a patch, run the test command to verify correctness.
- Use
apply_patchwithcreateaction for new files,modifyfor existing ones. - For large structural refactors, consider writing the full new file instead of a complex patch.
Approval Gates
Before marking a task complete, verify ALL of the following:
- Tests pass:
python3 -m pytest tests/ -x - Linting clean:
ruff check . && ruff format --check . - No unintended files modified (check
git diff --stat) - New code has corresponding tests (if behavior change)
- Commit message follows the project prefix convention
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.
- 2d ago First seen · 64 lines · 642 tokens per session scan A f1a5868ae375
agentmd AGENTS.md is an instructions file published in the GitHub repository mikiships/agentmd (12 stars, last pushed 5mo ago), licensed MIT. It adds 642 tokens to every session, about $0.0032 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
cocoindex-code CLAUDE.md
Instructions for cocoindex-io/cocoindex-code, covering claude.md, build and test commands, architecture, process model and key layers.
remind AGENTS.md
Instructions for sandst1/remind, covering remind - development guide for ai agents, project overview, architecture, key abstractions and data models (models.py).
terminal-jarvis AGENTS.md
Instructions for BA-CalderonMorales/terminal-jarvis, covering agents.md - terminal jarvis, current shape, key sections, branch strategy and merge-to-develop discipline.
ultracontext CLAUDE.md
Instructions for ultracontext/ultracontext, covering claude.md, architecture, context api (apps/api), sync (apps/sync) and mcp server (apps/mcp-server).
ultracontext AGENTS.md
Instructions for ultracontext/ultracontext, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
mosaic AGENTS.md
Instructions for hexxla/mosaic, covering project instructions, your responsibilities as an agent, hexagonal architecture, core concepts and layer responsibilities & rules.