agent-harness
CLAUDE.md2 starsChanged 2 days agoMITView on GitHub
This task runs inside a harness-managed worktree. - harness-cli is on PATH; HARNESS_* env vars are pre-set by the runner. - For agent-to-agent messaging via the agentboard, consult the harness-cli skill at .claude/skills/harness-cli/SKILL.md. - Your inbound agentboard topic is chat.<first-8-hex-of-HARNESS_TASK_ID>; the server subscribes you to it. There is no board-wide discovery topic. Read .claude/skills/implementation-pitfalls/SKILL.md — concrete past failure modes on this project (spec scope contraction, sibling-code pattern mismatch, peer.Conn vs objproto.Conn close semantics, bind-addr vs dial-addr confusion, etc.) plus subagent…
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- codebase-tourSkill
- harness-cli-from-a-toolSkill
- harness-cliSkill
- independent-reviewSkill
- landing-to-mainSkill
- memory-maintenanceSkill
- running-parallel-workersSkill
- session-debuggingSkill
- supervising-workersSkill
- codebase-tourSkill
- dummy-harnessSkill
- harness-cli-from-a-toolSkill
- harness-cliSkill
- implementation-pitfallsSkill
- independent-reviewSkill
- landing-to-mainSkill
- memory-maintenanceSkill
- running-parallel-workersSkill
- session-debuggingSkill
- supervising-workersSkill
- surface-parity-checklistSkill
The file
We split this CLAUDE.md 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 11
Read .claude/skills/implementation-pitfalls/SKILL.md — concrete past failure modes on this project (spec scope contraction, sibling-code …
≈ “Common” is an estimate: at least 1 in 5 of the 28,029 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.
Files
This task runs inside a harness-managed worktree.
harness-cliis on PATH;HARNESS_*env vars are pre-set by the runner.- For agent-to-agent messaging via the agentboard, consult the
harness-cliskill at.claude/skills/harness-cli/SKILL.md. - Your inbound agentboard topic is
chat.<first-8-hex-of-HARNESS_TASK_ID>; the server subscribes you to it. There is no board-wide discovery topic.
Before writing or reviewing code in this repo
Read .claude/skills/implementation-pitfalls/SKILL.md — concrete past
failure modes on this project (spec scope contraction, sibling-code
pattern mismatch, peer.Conn vs objproto.Conn close semantics, bind-addr
vs dial-addr confusion, etc.) plus subagent dispatch prompt augmentation
checklists. Cheaper to read it now than to rediscover by symptom.
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.

