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/orieg/yaml-workflow/agents-mdgit clone --depth 1 https://github.com/orieg/yaml-workflowWhat 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 | $0.00968 | $0.00968 |
| Opus 5 | $0.00484 | $0.00484 |
| Sonnet 5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
yaml-workflow 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents (Claude Code, Cursor, Copilot, and others) working in the yaml-workflow repository. Humans: see CONTRIBUTING.md.
What this project is
yaml-workflow is a lightweight Python workflow engine that runs tasks defined in YAML — shell, Python, file, template, HTTP, and batch — with Jinja2 templating, parallel execution, and resumable file-based state. The core runtime depends on only PyYAML and Jinja2; keep it that way — optional features (MCP server, web dashboard) live behind extras.
Setup
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -e ".[dev,test,doc]"
Build, test, and lint
pytest tests/ --benchmark-disable # run the test suite
pytest tests/test_shell_tasks.py::test_shell_basic # run a single test
black --check src tests # format check
isort --check-only --profile black src tests # import-order check
mypy src # type check
mkdocs build # build the docs site
Apply formatting with black src tests && isort --profile black src tests. Run
everything through the virtualenv (source .venv/bin/activate). CI runs black +
isort + mypy as a gate on Ubuntu / Python 3.12 before the tests, and runs
the test suite across Linux/macOS/Windows and Python 3.10–3.13 — so a change
must pass all four checks locally.
Code layout
src/yaml_workflow/engine.py— the workflow engine (parse, template, run, state).src/yaml_workflow/cli.py— CLI:run,list,validate,visualize,init,serve,serve-mcp.src/yaml_workflow/tasks/— built-in task types; register new ones with@register_task.src/yaml_workflow/validator.py— workflow validation (yaml-workflow validate).src/yaml_workflow/mcp_server.py— MCP server exposing workflows as agent tools.src/yaml_workflow/examples/— bundled example workflows (copied byyaml-workflow init).schema/workflow-schema.json— JSON Schema for the workflow YAML format.tests/— pytest suite, one file per module.docs/— MkDocs (Material) documentation source.
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 · 89 lines · 968 tokens per session scan A 84feb575e554
yaml-workflow AGENTS.md is an instructions file published in the GitHub repository orieg/yaml-workflow (3 stars, last pushed 9d ago), licensed MIT. It adds 968 tokens to every session, about $0.0048 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
pipelex AGENTS.md
Instructions for Pipelex/pipelex, covering pipelex coding rules, codex cloud commands, linting, keyword-only arguments check and cleaning derived files.
pipelex CLAUDE.md
Instructions for Pipelex/pipelex, covering pipelex coding rules, commands, linting, keyword-only arguments check and cleaning derived files.
workflow AGENTS.md
AGENTS.md instructions for vercel/workflow, covering agent instructions, architecture, core components, workflow execution model and development commands.
mosaicatcher-pipeline CLAUDE.md
Claude Code instructions for friendsofstrandseq/mosaicatcher-pipeline, covering claude.md, project overview, version management, common commands and using pixi (recommended for snakemake v9+).
NEEDLE CLAUDE.md
Instructions for jedarden/NEEDLE, covering needle project conventions, msrv, module dependency graph, code style and testing.
a-i--skills 03-development-workflow.instructions.md
Instructions for organvm-iv-taxis/a-i--skills, covering development workflow instructions, no repo-wide build system, common development commands, after adding/modifying skills and validation before committing.