edenbuildsedenbuilds/agentloop/.cursor/rules/harness-doctrine.mdc

agentloop / rules

Cursor rule0 starsChanged 4 months agoMITView on GitHub

agentloop harness doctrine always applied to agent work

Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,183 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 repository138 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/context-budget.mdcCursor rule
- .cursor/rules/delegation-law.mdcCursor rule
- .cursor/rules/verification-law.mdcCursor rule
- agent-interface-designSkill
- agentloop-coreSkill
- agent-loopSkill
- blindspot-passSkill
- brainstorm-prototypesSkill
- change-quizSkill
- conductor-planSkill
- context-auditSkill
- context-compactSkill
- context-surgeonSkill
- contrastingSkill
- deployment-auditSkill
- doctorSkill
- harness-designSkill
- humaniseSkill
- implementation-notesSkill
- implementation-planSkill
- interview-meSkill
- no-ai-slopSkill
- optional-ponytailSkill
- opus-promptingSkill
- persistent-memorySkill
- pev-cycleSkill
- pitch-packagerSkill
- progressive-disclosureSkill
- quality-composeSkill
- reference-huntSkill
- seo-copywritingSkill
- ship-gateSkill
- subagent-swarmSkill
- ui-ux-auditSkill
- warroom-councilSkill
- writer-verifierSkill
- agent-interface-designSkill
- agentloop-coreSkill
- agent-loopSkill
- blindspot-passSkill
- brainstorm-prototypesSkill
- change-quizSkill
- conductor-planSkill
- context-auditSkill
- context-compactSkill
- context-surgeonSkill
- contrastingSkill
- deployment-auditSkill
- doctorSkill
- harness-designSkill
- humaniseSkill
- implementation-notesSkill
- implementation-planSkill
- interview-meSkill
- no-ai-slopSkill
- optional-ponytailSkill
- opus-promptingSkill
- persistent-memorySkill
- The first 60 shown.

The file

We split this harness-doctrine.mdc into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Prefer quality composition over noisy swarms.
line 12
Very specific:
Prefer file-backed .agentloop/ artifacts for multi-step state.
line 14
Very specific:
Stop conditions in .agentloop/stop.yaml are hard (max_turns, no_progress, budget abort).
line 16
Very specific:
Every meaningful run refreshes .agentloop/handoff.md so another session can continue cold.
line 18

≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule 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

harness-doctrine.mdc

---
description: agentloop harness doctrine always applied to agent work
alwaysApply: true
---

agentloop doctrine:
- The harness owns control flow; the model reasons inside it.
- External verification defines done (tests/lint/types), not self-assurance.
- Finish the asked scope; one-sentence challenge allowed; no silent widening.
- Narration diet: brief start, sparse mid-flight, outcome-first finish.
- Methodological lenses only — never celebrity impersonation or fake endorsement.
- Prefer quality composition over noisy swarms; cap workers when parallel.
- Find unknowns before building; kill AI slop in copy and UI; humanise by default; ponytail voice only if asked.
- Prefer file-backed `.agentloop/` artifacts for multi-step state.
- Multi-step work uses Conductor Plan (`/plan`) with approval before expensive Execute.
- Stop conditions in `.agentloop/stop.yaml` are hard (max_turns, no_progress, budget abort).
- Context surgery is continuous policy (`context-surgeon`), not an occasional skill.
- Every meaningful run refreshes `.agentloop/handoff.md` so another session can continue cold.
- Persistent memory via `.agentloop/memory/` + `scripts/memory.sh` (local-first); handoff lists `memory_keys`; cloud sync reserved for later.

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