agentleFS
papagrationbiz-sketchpapagrationbiz-sketch/token-scrooge/skills/go-ceremony/SKILL.md

go-ceremony

Skill0 starsChanged 4 months agoMITView on GitHub

When to load — before editing or delegating any change to application code, or when deciding whether a user's reply counts as authorization to proceed. Covers the exact-match GO phrases, what does NOT count as GO, the stop-and-ask behavior, minor-work exceptions, and the rule against committing to the trunk branch.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Treat a reply as GO only if it is an exact match (not merely similar in meaning) to one of a small, predefined set of phrases.

    line 12
  2. Distinctive:

    When a reply does not exactly match the defined GO set, do not proceed with implementation.

    line 26
  3. Distinctive:

    Read-only investigation with no code changes

    line 44
  4. Distinctive:

    Never commit directly to the trunk/main branch, regardless of GO status or how minor the change is.

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

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

GO Ceremony

Application code must never be edited — directly or via delegation — before the user gives explicit, unambiguous authorization. This is a governance rule, not a suggestion: when in doubt, stop and ask.

Exact-match GO phrases

Treat a reply as GO only if it is an exact match (not merely similar in meaning) to one of a small, predefined set of phrases. The canonical example set used in the originating project was Japanese:

  • GO
  • この計画でGO
  • この計画で実装して

Projects and users are free to define their own exact-match set (in the user's language of choice) — the requirement is that the set be small, explicit, and checked for exact string match, not semantic similarity.

What does NOT count as GO

Any reply that is not an exact match to the defined set, however affirmative it sounds, does not authorize implementation. Examples (English): "OK", "Sounds good", "go ahead", "please do it", "yes". Examples (Japanese): OK / OKです / よさそう / 進めて / お願いします / やって. All such replies must be treated as not GO.

Stop-and-ask behavior

When a reply does not exactly match the defined GO set, do not proceed with implementation. Instead, return a short confirmation prompt restating that explicit GO is required, and list the accepted exact phrases. Then stop and wait.

Example confirmation prompt:

Starting implementation requires explicit GO. If you want me to proceed, please reply with one of:

- GO
- <your project's other exact-match phrases>

Minor-work exceptions

The following categories may skip the plan-review-and-GO ceremony (but never the trunk-commit rule below):

  • Typo fixes
  • Comment-only edits
  • Minor wording fixes in docs (README, etc.)
  • Read-only investigation with no code changes
  • Any case where the user has explicitly stated the work is minor and may proceed without ceremony

Trunk branch rule (absolute, no exceptions)

Never commit directly to the trunk/main branch, regardless of GO status or how minor the change is. All work happens on a branch; merging to trunk is the user's decision, made outside this ceremony.

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.