harness-engineer
Skill4 starsChanged 9 days agoApache-2.0View on GitHub
Plan and split multi-step agent work with Downshift. Use when the user names Downshift and asks how to split or parallelize subagent tasks, or why delegated work is not getting a smaller model.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- nurmdrafi/pi-nativetheir own version, first seen Oct 25, 2026
- fhgomes/my-awesome-agents-skillstheir own version, first seen Oct 13, 2026
- nihao555-hub/claude-code-agent-skillstheir own version, first seen Apr 1, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- fhgomes/my-awesome-agents-skills★ 5same name
- nihao555-hub/claude-code-agent-skills★ 4same name
- nurmdrafi/pi-native★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- downshift-layeringSkill
- architecture-coverageSkill
- downshift-auditSkill
- downshift-effortSkill
- downshift-orchestratorSkill
- downshift-setupSkill
- downshift-squadSkill
- downshift-tuneSkill
- ponytailSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Distinctive: line 10
Run parts in parallel when they share no file and no pending decision.
- Distinctive: line 11
Do 1–2 point parts yourself.
- Distinctive: line 12
Do not pin a model on mechanical subagents: Downshift can only right-size a spawn it may rewrite.
- Very specific: line 13
Check the result: downshift session --why (why each spawn got its model) and downshift report (tokens.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Harness engineer (basic)
- Restate the request in one sentence. If it can be read two ways, ask first.
- Estimate each part in story points (1, 2, 3, 5, 8, 13). Split any part of 8 or more.
- Run parts in parallel when they share no file and no pending decision.
- Do 1–2 point parts yourself; a spawn pays for its own context.
- Do not pin a model on mechanical subagents: Downshift can only right-size a spawn it may rewrite.
- Check the result:
downshift session --why(why each spawn got its model) anddownshift report(tokens; Compactor bytes stay separate).
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.