agentleFS
Sign inStart free
CodeAlive-AICodeAlive-AI/pragmatic-orchestration/AGENTS.md

pragmatic-orchestration

AGENTS.md45 starsChanged 52 days agoMITView on GitHub

Multi-skill repo shipped as one plugin. skills/<name>/ follows the canonical Agent Skills layout, read by both npx skills add (the cross-agent CLI) and Claude Code's plugin install (/plugin marketplace add + /plugin install …@pragmatic-orchestration). The plugin sees the repo root as itself via source: "./" in marketplace.json. Current skills: pragmatic-orchestration (the porch orchestration CLI) and remote-agents (dedicated remote Linux/Windows agent hosts). When the user asks to commit or push without naming a target branch, commit and push directly to main.…

  • Commits and pushes
  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository3 other files it gives its agents.

The file

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

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    When the user asks to commit or push without naming a target branch, commit and push directly to main.

    line 7
  2. Distinctive:

    Do not add beta or other prerelease suffixes unless the owner explicitly requests a prerelease.

    line 35
  3. Very specific:

    Follow semver. Skill/interface changes (skills/, .claude-plugin/*) require a version bump in BOTH .claude-plugin/plugin.json and …

    line 38

≈ “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

Pragmatic Orchestration — Development Guide

Multi-skill repo shipped as one plugin. skills/<name>/ follows the canonical Agent Skills layout, read by both npx skills add (the cross-agent CLI) and Claude Code's plugin install (/plugin marketplace add + /plugin install …@pragmatic-orchestration). The plugin sees the repo root as itself via source: "./" in marketplace.json. Current skills: pragmatic-orchestration (the porch orchestration CLI) and remote-agents (dedicated remote Linux/Windows agent hosts).

Git publishing defaults

When the user asks to commit or push without naming a target branch, commit and push directly to main. If the current branch is main, stay on it; do not create a feature branch by default. Use another branch only when the user explicitly requests one.

Naming

  • Skill names: pragmatic-orchestration, remote-agents (SKILL.md frontmatter, directory, state dirs).
  • CLI name: porch (scripts/porch, scripts/porch.cmd); remote-agents has no CLI of its own, its entry point is scripts/host.sh.
  • Environment variables: PORCH_* for orchestration; REMOTE_AGENTS_* for the host skill.
  • Historical name: agents-consilium / consilium — do not reintroduce.

Testing

Offline suite with fake backends — no network, no real provider CLIs:

cd skills/pragmatic-orchestration
bash scripts/tests/run.sh          # full harness (shell + python)
python3 scripts/tests/platform_test.py -v   # native-Python platform checks

Opt-in real-backend smoke tests: scripts/tests/steer/smoke_real.sh — see references/testing.md.

Versioning and releases

Owner's decision, 2026-10-30: use stable semver releases (for example, 2.1.0). Do not add beta or other prerelease suffixes unless the owner explicitly requests a prerelease.

Follow semver. Skill/interface changes (skills/**, .claude-plugin/*) require a version bump in BOTH .claude-plugin/plugin.json and .claude-plugin/marketplace.json (keep them in sync), then:

git tag -a vX.Y.Z -m "Version X.Y.Z" && git push origin vX.Y.Z
gh release create vX.Y.Z --title "vX.Y.Z — Title" --notes "Release notes"

Docs-only changes (README/AGENTS) do not need a release.

Configuration

skills/*/config.json is user-local and gitignored — pragmatic-orchestration's loader falls back to config.example.json, while remote-agents requires a real config.json (its example holds placeholders). remote-agents also keeps local bridge secrets/state under skills/remote-agents/.bridge-state/ (gitignored) — never commit credentials, private keys, or real infrastructure identifiers there or anywhere in the repo. Update config.example.json when a schema changes.

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