agentleFS
Sign inStart free
Cogni-AI-OUCogni-AI-OU/cogni-ai-agent-skills/.github/workflows/AGENTS.md

cogni-ai-agent-skills / workflows

AGENTS.md4 starsChanged 6 months agoMITView on GitHub

Authoritative, agent-facing catalog of workflows in this repository. Use this when loading or modifying workflows and keep it in sync with the files in this directory. For a human-readable overview, see README.md. - Purpose: run actionlint and pre-commit to enforce workflow and repo standards. - Triggers: push, pull_request, schedule, workflow_call, workflow_dispatch, workflow_run (after bot workflow completions). - Bot-PR support: workflow_run trigger enables checks on PRs created by bots, since normal pull_request events don't trigger for bot actors. - Reusable: uses:…

The file

We split this AGENTS.md into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep this catalog updated when workflows are added, removed, or renamed.

    line 78

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

GitHub Actions Workflows (Agent Catalog)

Authoritative, agent-facing catalog of workflows in this repository. Use this when loading or modifying workflows and keep it in sync with the files in this directory.

For a human-readable overview, see README.md.

Workflow catalog

  • check.yml: Linting and quality gates via actionlint and pre-commit.
  • cogni-ai-agent.yml: Logic for the Cogni AI Agent.
  • copilot-setup-steps.yml: Environment setup utility.
  • devcontainer-ci.yml: Build/test devcontainer and required tools/packages.
  • skill-validate.yml: Validate skills using gh skill publish --dry-run.

Details

check.yml

  • Purpose: run actionlint and pre-commit to enforce workflow and repo standards.
  • Triggers: push, pull_request, schedule, workflow_call, workflow_dispatch, workflow_run (after bot workflow completions).
  • Bot-PR support: workflow_run trigger enables checks on PRs created by bots, since normal pull_request events don't trigger for bot actors.
  • Reusable: uses: Cogni-AI-OU/cogni-ai-agent-skills/.github/workflows/check.yml@main.
  • Jobs: actionlint, link-checker, pre-commit.

cogni-ai-agent.yml

  • Purpose: provides the underlying logic to run the Cogni AI Agent.
  • Inputs: agent (default cogni-ai-architect).
  • Triggers: issue_comment, pull_request_review_comment, workflow_call, workflow_dispatch.
  • Details: Installs Python dependencies from .devcontainer/requirements.txt and calls the Cogni-AI-OU/cogni-ai-agent-action to process instructions.
  • Permissions: contents: write, id-token: write, issues: write, pull-requests: write.

copilot-setup-steps.yml

  • Purpose: utility workflow for setting up the environment.
  • Triggers: push and pull_request on copilot-setup-steps.yml or .devcontainer/requirements.txt.
  • Details: Checks out repo, sets up Python 3.12, restores cache, and installs dependencies.
  • Permissions: contents: read.

devcontainer-ci.yml

  • Purpose: build and validate the dev container; ensure required tools and Python packages exist.
  • Inputs: required_commands (defaults to common CLI tools), required_python_packages (defaults to ansible, ansible-lint, docker, molecule, pre-commit, uv).
  • Triggers: pull_request/push affecting .devcontainer/ or this workflow; weekly schedule; workflow_call.
  • Permissions: callers must grant packages: write when pushing images to GHCR.
  • Reusable: uses: Cogni-AI-OU/cogni-ai-agent-skills/.github/workflows/devcontainer-ci.yml@main.

skill-validate.yml

  • Purpose: run gh skill publish --dry-run to validate skills.
  • Triggers: pull_request, push, workflow_dispatch.
  • Permissions: contents: read.

Notes

Model options list

The model input options for workflow_dispatch must be identical in the corresponding workflow files:

FileLocation
cogni-ai-agent.ymlworkflow_dispatch inputs

Agent options list

The agent input options for workflow_dispatch must be identical in the corresponding workflow files:

FileLocation
cogni-ai-agent.ymlworkflow_dispatch inputs
  • Keep this catalog updated when workflows are added, removed, or renamed.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free