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/microsoft/apm/lintinggit clone --depth 1 https://github.com/microsoft/apmWhat 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 | $0.00826 | $0.00826 |
| Opus 5 | $0.00413 | $0.00413 |
| Sonnet 5 | $0.00165 | $0.00165 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
apm linting.instructions.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.
This is a copy
94% identical to apm copilot-instructions.md — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linting (canonical contract)
The CI Lint job is a hard gate. Mirror it locally before git push
and before producing any artifact (PR body, release note, audit
report) that claims CI is green.
CI-mirror commands
The Lint job runs (see .github/workflows/ci.yml):
uv run --extra dev ruff check src/ tests/uv run --extra dev ruff format --check src/ tests/- YAML I/O safety guard (rejects raw
yaml.dump(..., handle)outsideutils/yaml_io.py; mark approved exceptions with# yaml-io-exempt). - File length guardrail (no
src/**/*.pymay exceed 2450 lines). - No raw
str(path.relative_to(...))patterns -- useportable_relpath()fromapm_cli.utils.paths. - Code duplication guardrail (pylint R0801):
uv run --extra dev python -m pylint --disable=all --enable=R0801 \ --min-similarity-lines=10 --fail-on=R0801 src/apm_cli/ - Auth-protocol boundary check:
bash scripts/lint-auth-signals.sh
All seven must succeed. CI evaluates these on the PR merge commit
(HEAD merged with current main), so duplication introduced by a
recent main commit can fail your PR even if your own diff is clean.
Always merge main locally before running the mirror.
Local workflow
- Auto-fix style+imports:
uv run --extra dev ruff check src/ tests/ --fix - Apply formatter:
uv run --extra dev ruff format src/ tests/ - Verify the full Lint job (must all be silent / exit 0):
(The YAML, file-length, anduv run --extra dev ruff check src/ tests/ \ && uv run --extra dev ruff format --check src/ tests/ \ && uv run --extra dev python -m pylint --disable=all --enable=R0801 \ --min-similarity-lines=10 --fail-on=R0801 src/apm_cli/ \ && bash scripts/lint-auth-signals.shrelative_toguards are pure-grep one-liners fromci.yml; run them directly if you have touched those surfaces.)
Always run the verify chain before git push -- the CI Lint job
fails on any remaining diagnostic.
Common surprises
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 · 70 lines · 826 tokens per session scan A 8d31137f1884
apm linting.instructions.md is an instructions file published in the GitHub repository microsoft/apm (3,668 stars, last pushed 2d ago), licensed MIT. It adds 826 tokens to every session, about $0.0041 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to apm copilot-instructions.md, differing in 5 lines, and is treated as a copy.
Other instructions, from other repositories
aru AGENTS.md
Instructions for narumiruna/aru, covering repository guidance, scope and authority, communication & documentation, code style and project map.
skillport AGENTS.md
Instructions for gotalab/skillport, covering agent guidelines & context, 1. core principles (10-second recall), 2. project context, architecture and directory structure.
odin-codex-plugin AGENTS.md
Instructions for OutlineDriven/odin-codex-plugin, covering codex coding agent adherences, token-efficient cli output, tool hierarchy, core system & file ops and search & discovery.
copilot-setting AGENTS.md
AGENTS.md instructions for zexion7873/copilot-setting, covering copilot-setting — agent guide, communication language, repository purpose, validation commands and architecture.
loadout reactjs.instructions.md
ReactJS Engineering Instructions.
loadout tauri.instructions.md
Tauri Engineering Instructions.