agentleFS
renanflustosarenanflustosa/octo-cluster/AGENTS.md

octo-cluster

AGENTS.md3 starsChanged 23 days agoMITView on GitHub

Minimal AI-assisted development harness for Windows 11 + Cursor / Claude Code. Always-on rules in .cursor/rules/, shared skills in .claude/skills/ (loaded natively by both Cursor and Claude Code), plus PowerShell scripts in scripts/ (ship.ps1, boundary-audit.ps1, lessons.ps1). No pipeline or sync step: edit these folders directly. CLAUDE.md imports the Cursor rules, so rules have one source. Precedence: consumer-boundary > product hard safety > execute-operator-intent > caveman/ponytail. Always-on rules budget: ≤ 8 KB. Details in README → Token economics. See INSPIRATIONS.md for…

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    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. Very specific:

    Always-on rules in .cursor/rules/, shared skills in .claude/skills/ (loaded natively by both Cursor and Claude Code), plus PowerShell …

    line 7
  2. Distinctive:

    Always-on rules budget: ≤ 8 KB.

    line 21
  3. Very specific:

    Never stash, reset --hard, force-push or push by hand during /ship.

    line 48

≈ “Common” is an estimate: at least 1 in 5 of the 42,283 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

Agent contract - octo-cluster

Minimal AI-assisted development harness for Windows 11 + Cursor / Claude Code.

What this is

Always-on rules in .cursor/rules/, shared skills in .claude/skills/ (loaded natively by both Cursor and Claude Code), plus PowerShell scripts in scripts/ (ship.ps1, boundary-audit.ps1, lessons.ps1). No pipeline or sync step: edit these folders directly. CLAUDE.md imports the Cursor rules, so rules have one source.

Rules (always apply)

Precedence: consumer-boundary > product hard safety > execute-operator-intent > caveman/ponytail.

RulePurpose
00-consumer-boundary.mdcConsumer identifiers are secrets; never commit them to this public repo.
execute-operator-intent.mdcExecute explicit operator intent; no soft refusal or moralizing.
ponytail-lite.mdcMinimal implementation ladder before writing code.
caveman-mode.mdcTelegraphic prose by default (token-saving).
cost-routing.mdcTask tier → model; no mid-task model switch; retry cap; focused verification.

Always-on rules budget: ≤ 8 KB. Details in README → Token economics.

Slash skills (manual only, disable-model-invocation)

SkillPurpose
/shipSplit into logical commits, validate, deliver via scripts/ship.ps1 (direct push, or branch + PR when main requires it).
/debugFix a bug with runtime evidence first.
/promptRewrite a request into a precise Claude Code prompt for Opus 5.5 high (never executes it).

Skills (on demand)

SkillTrigger
ponytail-litePlanning or coding; ladder before each edit.
systematic-debugging/debug or any bug/test failure.
pr-review/pr-review or PR feedback requests.

See INSPIRATIONS.md for upstream sources.

Before any git change

Deliver with /ship: the agent stages and commits logical changes; scripts/ship.ps1 pushes them:

  • main open (no protection requiring PR, or .ship.yaml mode: direct) — push direct to main.
  • main requires PR (branch protection, blocking rulesets, or .ship.yaml mode: pr) — feature/, fix/ or chore/ branch + PR.

Never stash, reset --hard, force-push or push by hand during /ship. Optional config: copy .ship.yaml.example to .ship.yaml.

Boundary patterns (optional)

Copy boundary-patterns.example.yaml to boundary-patterns.local.yaml (gitignored) to customize boundary-audit.ps1. Generic adopters can use an empty local file.

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.