harness-review
Skill0 starsChanged 28 days agoMITView on GitHub
Review an agent's harness (scaffold) for quality, token efficiency, and correctness. Based on harness engineering research.
12 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- maxwell2732/claudecode-research-harness-workflowtheir own version, first seen Nov 15, 2026
- AbhishekAshtekarDev/harness-engineeringtheir own version, first seen Nov 8, 2026
- naman10parikh/wikimemedited, first seen Nov 8, 2026
- naman10parikh/turboword for word, first seen Oct 25, 2026
- naman10parikh/pixelword for word, first seen Oct 25, 2026
- naman10parikh/agentgridedited, first seen Oct 20, 2026
Other versions12 projects use a version of this.
Word for word · 2
- naman10parikh/pixel★ 0100% same
- naman10parikh/turbo★ 0100% same
Edited · 2
- naman10parikh/agentgrid★ 998% same
- naman10parikh/wikimem★ 898% same
Wrote their own version · 8
- Chachamaru127/claude-code-harness★ 3.2ksame name
- maxwell2732/claudecode-research-harness-workflow★ 42same name
- BenjaminG/ai-skills★ 4same name
- HACK-WU/skills★ 3same name
- MrBogomips/agentic-harness★ 1same name
- thefacelessdon/facework★ 1same name
- AbhishekAshtekarDev/harness-engineering★ 0same name
- daikubo-jb/my-claude-harness★ 0same 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 repository33 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- agent-runtimeSkill
- frontend-designSkill
- architectSkill
- deep-thinkSkill
- design-systemsSkill
- ecosystem-referenceSkill
- fractal-delegationSkill
- heartbeatSkill
- integrate-resourcesSkill
- llm-council-critiqueSkill
- loop-createSkill
- mcp-setupSkill
- memory-compressionSkill
- memorySkill
- model-routingSkill
- oss-project-scaffoldSkill
- playwright-cliSkill
- repo-scoutSkill
- self-improveSkill
- skill-creatorSkill
- skill-routingSkill
- sprintSkill
- test-visualSkill
- troubleshootSkill
- ux-auditSkill
- agent-spend-credentialSkill
- metered-billingSkill
- stripe-version-migrationSkill
- stripe-webhook-correctnessSkill
- subscription-prorationSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
0
Distinctive
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 51
Read docs/vision/the_complete_story.md — search for "harness engineering evidence"
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
The Core Insight
Same model with scaffold A scores 42%. Same model with scaffold B scores 78%. The harness IS the product.
Review Checklist
1. Context Loading
- Bootstrap memory under 2,000 tokens?
- Skills loaded on-demand, not all upfront?
- Total input under 40% of context window? (the "dumb zone" is past 60%)
2. Tool Design
- Each tool has a clear, one-sentence description?
- Failed tool calls return actionable error messages (not stack traces)?
- Tool results are concise (no dumping raw HTML/JSON)?
3. Error Recovery
- Retry logic with exponential backoff?
- Graceful degradation (if tool X fails, try alternative)?
- Never silent swallowing of errors?
4. Model Routing
- Parsing/extraction tasks → cheapest tier (Haiku)?
- Reasoning/planning → middle tier (Sonnet)?
- Architecture/complex decisions → top tier (Opus)?
- Never sending 100K tokens to the expensive model?
5. Memory Management
- Important facts written to disk BEFORE compaction?
- Memory files have clear structure (not just append-only)?
- Cross-session memory actually loads at session start?
6. Planning
- Uses TodoWrite or equivalent for multi-step coherence?
- Each step has a testable definition of done?
- Can explain what it's doing and why at any point?
Reference
Read docs/vision/the_complete_story.md — search for "harness engineering evidence"
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.

