pr-shepherd-contract
Skill396 starsChanged 6 months agoMITView on GitHub
GitHub adapter binding for the shepherd contract: turn a real pull request into observed events, resolve the responsible actor from commit authorship, and persist the waiting contract under the workspace so a later pass (or process) can resume it.
In this repository73 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-activitySkill
- agent-registrySkill
- agent-room-opsSkill
- answer-formatSkill
- audio-transcribeSkill
- bee-actionsSkill
- bot2bot-postSkill
- call-diagnosticsSkill
- claude-codexSkill
- claude-geminiSkill
- claude-piSkill
- claude-routerSkill
- collaboration-intelligenceSkill
- connect-appsSkill
- context-dropSkill
- context-reconstructSkill
- db-browserSkill
- deal-finderSkill
- doc-ingestSkill
- electron-overlay-dimmingSkill
- email-findSkill
- engine-conflict-resolveSkill
- gemini-ttsSkill
- image-generationSkill
- import-claude-contextSkill
- local-workspace-serverSkill
- macos-toolsSkill
- macos-useSkill
- make-viral-videoSkill
- marketplaceSkill
- media-transcriptSkill
- meeting-prepSkill
- meeting-schedulerSkill
- mention-gateSkill
- model-switchSkill
- morning-briefingSkill
- ms365-connectSkill
- observeSkill
- obsidian-vaultSkill
- openai-ttsSkill
- open-sutando-refSkill
- overlay-appsSkill
- phone-conversationSkill
- proactive-loopSkill
- quota-trackerSkill
- regression-searchSkill
- relaySkill
- releaseSkill
- report-feedbackSkill
- review-preflightSkill
- room-collabSkill
- schedule-cronsSkill
- screen-companionSkill
- screen-recordSkill
- self-diagnoseSkill
- self-upgradeSkill
- session-recapSkill
- skill-usage-reportSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 26
Import from the skill's scripts directory (the module bootstraps src/ onto sys.path itself):
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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.
Files
PR Shepherd Contract (GitHub adapter)
The GitHub binding for the provider-neutral shepherd contract
(src/shepherd_contract.py). The contract defines WHAT a shepherd task is
responsible for and WHICH observed events count; this skill supplies the
GitHub-specific half:
- Observation —
observe(repo, number)reads live PR state via the GitHub CLI (gh api) and emits oneObservedEvent(merged / closed unmerged / updated). - Actor resolution —
resolve_actor(repo, number)uses the last non-merge commit's author email (git.commit_author_email), not the account login, because several actors can push under one login. - Persistence —
save(task_id, scope, state)/load(task_id)/resume(task_id)keep the durable contract record under<workspace>/state/shepherd/, create-or-advance only (never rebind), so a different process can pick the objective up later.
Usage
Import from the skill's scripts directory (the module bootstraps src/ onto
sys.path itself):
import sys, pathlib
sys.path.insert(0, str(repo_root / "skills" / "pr-shepherd-contract" / "scripts"))
import shepherd_github as g
scope = g.scope_for("owner/repo", 123, g.resolve_actor("owner/repo", 123))
g.save("task-abc", scope, "waiting", "shepherding PR 123")
# ... later, any process:
state, why = g.resume("task-abc")Tests: tests/shepherd-github-durability.test.py,
tests/shepherd-github-integrity.test.py (contract policy itself:
tests/shepherd-contract-admission.test.py).
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
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.

