agentleFS
Sign inStart free
MaleickMaleick/AutoShip/AGENTS.md

AutoShip

AGENTS.md4 starsChanged 6 months agoMITView on GitHub

AutoShip is an OpenCode-only GitHub issue → pull request orchestration plugin. See AGENT_CATALOG.md for the specialized agent roles, inputs, outputs, boundaries, and default model families. Core orchestration hooks in hooks/opencode/: - plan-issues.sh - Plan eligible issues from GitHub - dispatch.sh - Dispatch workers to issues - runner.sh - Execute workers - reviewer.sh - Review worker output - create-pr.sh - Create PR from approved work - verify-result.sh - Verify worker results - monitor-agents.sh - Monitor running workers - monitor-ci.sh - Monitor…

  • 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 31,774 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 repositoryOne other file it gives its agents.

The file

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

7 rules. About 0 are common, 2 are distinctive, and 5 are 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.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Prefer capable free models first, then OpenCode Go role models when available.

    line 12
  2. Distinctive:

    Default active worker cap is 20 for both OpenCode and Hermes.

    line 15
  3. Distinctive:

    Before claiming work is complete, run:

    line 64
  4. Very specific:

    Keep README, docs/, and the GitHub Wiki aligned with OpenCode-only messaging.

    line 73
  5. Very specific:

    Before answering architecture or codebase questions, read graphify-out/GRAPH_REPORT.md for god nodes and community structure

    line 80
  6. Very specific:

    If graphify-out/wiki/index.md exists, navigate it instead of reading raw files

    line 81
  7. Very specific:

    After modifying code files in this session, run graphify update .

    line 83

≈ “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

AutoShip Agent Guide

AutoShip is an OpenCode-only GitHub issue → pull request orchestration plugin.

See AGENT_CATALOG.md for the specialized agent roles, inputs, outputs, boundaries, and default model families.

Runtime Policy

  • OpenCode is the primary supported worker runtime.
  • Hermes is supported as an alternative runtime via hooks/hermes/.
  • Role models are selected from live opencode models inventory and .autoship/model-routing.json; do not assume openai/gpt-5.5 is available or preferred.
  • Prefer capable free models first, then OpenCode Go role models when available; use Kimi/Kimmy 2.6 only through opencode-go/* unless the operator explicitly selects another supported provider model.
  • openai/gpt-5.5-fast is not allowed.
  • Worker models come from live opencode models inventory and are routed free-first with deterministic rotation across compatible workers.
  • Default active worker cap is 20 for both OpenCode and Hermes.
  • Plan agent:ready issues in ascending issue-number order (unless AUTOSHIP_PLAN_ORDER is set).

Available Hooks

Core orchestration hooks in hooks/opencode/:

  • plan-issues.sh - Plan eligible issues from GitHub
  • dispatch.sh - Dispatch workers to issues
  • runner.sh - Execute workers
  • reviewer.sh - Review worker output
  • create-pr.sh - Create PR from approved work
  • verify-result.sh - Verify worker results
  • monitor-agents.sh - Monitor running workers
  • monitor-ci.sh - Monitor PR CI checks
  • auto-merge.sh - Merge opted-in PRs after CI passes
  • reconcile-state.sh - Reconcile state

Hermes runtime hooks in hooks/hermes/:

  • setup.sh - Discover Hermes capabilities, write hermes-model-routing.json
  • plan-issues.sh - Plan issues for Hermes dispatch (uses autoship:ready-simple label)
  • dispatch.sh - Create worktree and write HERMES_PROMPT.md
  • runner.sh - Prepare Hermes workspaces for manual delegate_task dispatch
  • status.sh - Show Hermes runtime status
  • cronjob-dispatch.sh - Generate Hermes cronjob specs for queued issues

Safety hooks:

  • sanitize-issue.sh - Prompt-injection guardrails (#271)
  • diff-size-guard.sh - Diff size guardrail (#280)
  • anti-flake.sh - Anti-flake test retry (#282)
  • classify-issue.sh - Protected label guards (#258)
  • worktree-checksum.sh - Worktree checksum/scope reports (#260)
  • quota-guard.sh - Free-model quota pause/resume guardrail (#284)

Utilities:

  • check.sh - Pre-commit verification umbrella (#269)
  • gh-retry.sh - GitHub API retry with backoff (#257)
  • item-record.sh - Per-issue durable records (#259)
  • extract-criteria.sh - Acceptance criteria extraction (#278)
  • audit.sh - GitHub/local drift audit (#256)
  • dashboard.sh - Metrics dashboard (#266)
  • pr-body.sh - Structured PR descriptions (#279)
  • policy-hash.sh - Plan invalidation policy hash (#264)

Local State

.autoship/ is runtime state and must not be committed.

Verification

Before claiming work is complete, run:

bash hooks/opencode/check.sh
bash -n hooks/opencode/*.sh hooks/*.sh

Docs

Keep README, docs/, and the GitHub Wiki aligned with OpenCode-only messaging.

graphify

This project has a graphify knowledge graph at graphify-out/.

Rules:

  • Before answering architecture or codebase questions, read graphify-out/GRAPH_REPORT.md for god nodes and community structure
  • If graphify-out/wiki/index.md exists, navigate it instead of reading raw files
  • For cross-module "how does X relate to Y" questions, prefer graphify query "<question>", graphify path "<A>" "<B>", or graphify explain "<concept>" over grep — these traverse the graph's EXTRACTED + INFERRED edges instead of scanning files
  • After modifying code files in this session, run graphify update . to keep the graph current (AST-only, no API cost)

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