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/comfy-org/github-workflows/agents-mdgit clone --depth 1 https://github.com/Comfy-Org/github-workflowsWhat 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 | $0.02855 | $0.02855 |
| Opus 5 | $0.01427 | $0.01427 |
| Sonnet 5 | $0.00571 | $0.00571 |
| Haiku 4.5 | $0.00285 | $0.00285 |
Grade A, and why
github-workflows 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.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Comfy-Org/github-workflows
Shared, versioned reusable GitHub Actions workflows used across Comfy-Org repositories. This repo is public, so any repo — public or private, in the org or out — can call them. Each workflow's logic (prompts, Python/shell scripts) lives here as the single source of truth; consumers carry only a thin caller pinning this repo by full commit SHA. Nothing is built or run — the workflows ARE the deliverable.
Commands
Python is stdlib-only, with ONE exception: .github/coderabbit-config/ needs a
YAML parser and a JSON Schema validator, pinned in requirements.txt (exact
versions + sha256, installed --require-hashes). CI uses Python 3.12; there
is no repo-wide formatter config. Run from the repo root. Every suite is mirrored
by a path-filtered .github/workflows/test-*.yml, and that workflow — not the
list below — is the authority on the exact command; read the matching one for
whatever you touched.
# Python suites — agents-md-integrity, coderabbit-config, cursor-review, groom,
# linear-ticket, public-repo-hygiene, refresh-reviewers, workflow-pins:
python3 -m unittest discover -s <dir>/tests -p 'test_*.py' -v
# coderabbit-config first: pip install --require-hashes --only-binary=:all: -r <its requirements.txt>
# Shell suites — area-label, bump-callers, groom, pr-derisk, pr-risk (gh/model
# stubbed; no network). Glob `tests/*.sh`, not `test_*.sh` — groom's confinement
# suite is `sandbox-tests.sh` — and LOOP: `bash a.sh b.sh` runs only `a.sh`.
shellcheck -x <dir>/*.sh <dir>/tests/*.sh
for t in <dir>/tests/*.sh; do bash "$t" || { echo "FAILED: $t"; break; }; done
# shellcheck-only, no suite: .github/cursor-review/{install-cursor-cli,slack-notify}.sh
# Go — scripts/check-pr-size; its tests sit beside the source, not in tests/:
(cd scripts/check-pr-size && [ -z "$(gofmt -l .)" ] && go vet ./... && go test ./...)
# Repo-wide lints that take a target rather than a suite:
python3 .github/workflow-pins/check_workflow_pins.py # no reusable may default `workflows_ref`
python3 .github/agents-md-integrity/check_agents_md.py --root .
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.
- yesterday First seen · 156 lines · 2,855 tokens per session scan A 9f0bfcd5127e
github-workflows AGENTS.md is an instructions file published in the GitHub repository Comfy-Org/github-workflows (5 stars, last pushed 3d ago), licensed MIT. It adds 2,855 tokens to every session, about $0.0143 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.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.