agentleFS
PhlegonlabsPhlegonlabs/product-delivery-harness/CLAUDE.md

product-delivery-harness

CLAUDE.md1 starsChanged 18 days agoMITView on GitHub

The rules below apply only when this session is executing a managed Product Delivery Harness PLAN/RUN mission. Direct work follows AGENTS.md and the user's request without creating Harness state or worker topology.

The file

We split this CLAUDE.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
  1. Distinctive:

    Only within an explicitly requested skill workflow from this suite, follow the shared document-sync and bounded-enhancement rules in …

    line 7
  2. Distinctive:

    Treat AGENTS.md as the shared repository governance imported above.

    line 8
  3. Very specific:

    After serial integration, the parent dispatches one fresh read-only reviewer on the unified head carrying code, visual when UI changed, and …

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.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
CLAUDE.md

Project Instructions

@AGENTS.md

Runtime Boundary

  • Only within an explicitly requested skill workflow from this suite, follow the shared document-sync and bounded-enhancement rules in AGENTS.md; keep runtime-specific instructions here. Preserve existing owner text when an authorized pointer correction is needed, and never copy one runtime's instructions over another's.
  • Treat AGENTS.md as the shared repository governance imported above. Preserve the current host's effective context discovery.
  • For explicitly requested managed execution, use the general runtime adapter reference (delivery-harness/references/runtime-adapters.md) to map observed native tools to the shared capability contract. The parent retains authorization; host names do not choose launch APIs, roles or models.

The rules below apply only when this session is executing a managed Product Delivery Harness PLAN/RUN mission. Direct work follows AGENTS.md and the user's request without creating Harness state or worker topology.

Managed Harness Missions

  • A mission worker is one bounded writer. It never delegates, edits parent-owned PLAN/RUN state, integrates, pushes, or cleans up. Authorization for those actions remains with the Harness parent and does not transfer to the worker.
  • Explorers, mission writers, and reviewers are parent-dispatched siblings. Each writer has explicit file ownership and a separate clean exact-base worktree.
  • After serial integration, the parent dispatches one fresh read-only reviewer on the unified head carrying code, visual when UI changed, and the security lens in delivery-harness/references/security-review.md, then runs one broad final validation after it passes.
  • Harness 0.38+ RUNs close locally. Only the parent may later archive candidate C, commit and reverify archive-only A, and—under separate action-time authorization—publish A by exact-authorized no-force push and remote readback. No Claude worker receives that authority.
  • Return the exact worktree, branch, head SHA, changed files, verifier evidence, and blocking state through the completion channel supplied by the Harness parent.

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.