agentmods.dev

crewplane AGENTS.md

The main repository guide for Crewplane, a Python command-line tool that runs multi-agent workflows described in Markdown. It explains the project's file-based coordination model and supported operating systems.

In plain words
What is it for?
Use it for changes to Crewplane's configuration, workflow parsing, provider integrations, runtime, filesystem artifacts, observability, or tests.
Why use it?
It helps agents preserve reviewable workflow artifacts, clear system boundaries, cross-platform support, and deterministic tests when changing behavior.

Instructions file for CodexOpenCode

35 4d ago A scan 2,548 tokens original Apache-2.0
View the source file crewplaneai/crewplane
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/crewplaneai/crewplane/agents-md
Clone the repo
git clone --depth 1 https://github.com/crewplaneai/crewplane

Made for: Codex, OpenCode.

Per session 2,548 This file is loaded in full into every session.
When invoked 2,548 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 $0.02548 $0.02548
Opus 5 $0.01274 $0.01274
Sonnet 5 $0.00510 $0.00510
Haiku 4.5 $0.00255 $0.00255

Measured 2d ago against content hash 2b818cd9595e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

crewplane 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.

AGENTS.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Canonical repository instructions for coding agents.

Use this file for repo-wide agent behavior. Use DEVELOPMENT.md for broader engineering context and maintenance notes. More specific AGENTS.md files in subdirectories override this file for their subtree.

Repo Facts

crewplane is a Python 3.13+ Typer CLI for running multi-agent workflows defined in Markdown. The core architectural rule is blackboard-style orchestration: providers do not coordinate through shared in-memory state; they communicate through artifacts written under .crewplane/.

Crewplane supports Linux, macOS, and WSL. Native Windows is not supported.

When changing behavior, preserve these properties:

  • CLI-first provider integration. The project is built around external AI CLIs, not vendor SDKs.
  • Auditable execution. Inputs, intermediate outputs, manifests, and results stay on disk as readable files.
  • Explicit boundaries. Config loading, workflow parsing/composition, adapter resolution, provider invocation, runtime execution, artifacts, and observability are separated on purpose.
  • Deterministic validation. New behavior should be covered by filesystem-local pytest tests, and mock-driven end-to-end checks should stay available.

Read First

  • README.md: short package and repository orientation
  • docs/index.md: full public user documentation
  • DEVELOPMENT.md: human-facing setup, quality gates, repo layout, and local validation workflows
  • docs/architecture/index.md: architecture entry point and ADR links

Repo Map

  • src/crewplane/cli/: Typer command surface, task/config path resolution, run orchestration, cleanup commands, scaffold templates
  • src/crewplane/core/: config models, workflow schemas, Markdown parsing, workflow composition/imports, DAG validation, preflight compilation, schema version validation
  • src/crewplane/architecture/: port contracts, integration loader, alias registry, adapter errors
  • src/crewplane/bootstrap/: composition root that wires configured adapters into runtime components
  • src/crewplane/runtime/: provider invocation, retry/quota handling, parallel/sequential workflow execution
  • src/crewplane/artifacts/: stage/result directories, manifests, generated files, locks, result writing, resume, workspace state, output access
  • src/crewplane/observability/: event model, runtime snapshots, rendering, tmux support
  • src/crewplane/adapters/: built-in invoker, UI, and artifact implementations
  • src/crewplane/example_templates/: files used by crewplane init
  • tests/: CLI, config, workflow, runtime, observability, adapter, and architecture coverage

Read the full file on GitHub · 199 lines

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. 2d ago First seen · 199 lines · 2,548 tokens per session scan A 2b818cd9595e

Subscribe to this mod's changes

crewplane AGENTS.md is an instructions file published in the GitHub repository crewplaneai/crewplane (35 stars, last pushed 4d ago), licensed Apache-2.0. It adds 2,548 tokens to every session, about $0.0127 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.

Building agentsagent-control-planeagent-orchestrationai-codingclaude-codeclicodex-cli
Related

Other instructions, from other repositories

map-framework CLAUDE.md

Instructions for azalio/map-framework, covering map framework (mapify-cli) — agent instructions, what this repo is, critical invariant: template single-source render, skill catalog invariant and how to work in this repo.

azalio/map-framework · 1,601 tokens

intuitive-flow AGENTS.md

Instructions for MiaoDX/intuitive-flow, covering codex guide, environment, delegation and verification, development and testing and preferred skills and workflow routing.

MiaoDX/intuitive-flow · 1,431 tokens

gluon-agent CLAUDE.md

Instructions for carrotly-ai/gluon-agent, covering claude.md, what is gluon agent?, llm providers, docker operations and dev/test (build from source).

carrotly-ai/gluon-agent · 5,431 tokens

SubFrame CLAUDE.md

Instructions for Codename-11/SubFrame, covering subframe, core rule, architecture, tech stack and key modules.

Codename-11/SubFrame · 5,031 tokens

codex-harness-javascript AGENTS.md

Instructions for thuandiep1707/codex-harness-javascript, covering codex multi-agent delivery system, system truths, public workflow registry vs internal capabilities, public workflows and internal capabilities.

thuandiep1707/codex-harness-javascript · 4,411 tokens

AgentsMesh CLAUDE.md

Claude Code instructions for AgentsMesh/AgentsMesh, covering claude.md, project overview, components, development environment and quick start.

AgentsMesh/AgentsMesh · 8,503 tokens