harness-engineering
Skill1 starsChanged 2 months agoMITView on GitHub
Claude Code bridge that points to the canonical Harness Engineering entry in SKILL.md.
27 other projects use a version of this.
Adopted by
Most recently taken up by
- wxxb789/hoatheir own version, first seen Nov 16, 2026
- dvy1987/agent-loomtheir own version, first seen Nov 15, 2026
- AnonymXXX/codex-harness-engineeringtheir own version, first seen Nov 10, 2026
- anuragsarkar97/skillstheir own version, first seen Nov 8, 2026
- Mark393295827/graph-engineering-architecturestheir own version, first seen Nov 8, 2026
- docxology/templatetheir own version, first seen Oct 30, 2026
Used with
Projects with it also use self-improvement-loops, bdi-mental-states and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
DVwebBiz11Skillself-improvement-loops
This skill should be used when the harness, scaffold, workflow, or optimizer itself is the optimization target: recursive self-improvement (RSI) loops, meta-harnesses, self-improving harnesses that mine their own failures and propose bounded edits, evolutionary or population-based search over agent scaffolds, acceptance gates for self-modifying systems, and agentic context evolution where the mechanism that produces context is versioned and evolved. Route governance of a single autonomous loop (locked surfaces, durable logs, rollback, novelty gates, approval boundaries) to harness-engineering, measurement and quality-gate design to evaluation, judge design to advanced-evaluation, and remote sandbox infrastructure to hosted-agents.
Also in 4 projects that use this
Downey6689Skillbdi-mental-states
Transforms external RDF context into BDI mental states. Invoke when modeling beliefs, desires, and intentions.
Also in 5 projects that use this
Downey6689Skillhosted-agents
Guidance for hosted/sandboxed agents. Invoke when running background agents in isolated VMs or multi-client setups.
Also in 5 projects that use this
DVwebBiz11Skilllong-horizon-prompting
This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent orchestration attacking a hard problem: pseudo-formal task briefs that define terms and an exact success predicate linguistically, enumerate non-counting outcomes, set persistence rules with explicit stop and return conditions and effort floors, manage a diverse portfolio of parallel approaches with an approach registry and blocked-route bookkeeping, and gate the return on adversarial audit. Route agent topology and coordination protocols to multi-agent-patterns, runtime control surfaces and loop governance to harness-engineering, evaluator and quality-gate construction to evaluation, judge design to advanced-evaluation, and compaction or memory mechanics to context-compression and memory-systems.
Also in 4 projects that use this
AbdelrhmanAlquranSkilllatent-briefing
This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce worker tokens", "cross-agent memory without summarization", or discusses Attention Matching compaction, recursive language models with workers, or token explosion in hierarchical agents.
Also in 4 projects that use this
abdullah1854Skillcontext-degradation
Also in 5 projects that use this
- +2 more from Downey6689
Other versions27 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 27
- github/awesome-copilot★ 41ksame name
- muratcankoylan/Agent-Skills-for-Context-Engineering★ 18ksame name
- kangarooking/kangarooking-skills★ 709same name
- magnus919/agent-skills★ 177same name
- brake71/1c-ssl-skills★ 85same name
- docxology/template★ 24same name
- charlesanim/harness-engineering★ 20same name
- fiveonecode/agent-skills★ 20same name
- DamonZS/Claude-Codex-Pro-Tool★ 15same name
- drewid74/ai_skills★ 8same name
17 more not listed
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 repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- deployment/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- goalSkill
- harness-engineeringSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 24 edited versions we read keep these.
10
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use the canonical skill body at:
- Distinctive: line 22
When executing inside Claude Code:
- Distinctive: line 26
Read only the canonical references required for the chosen scope.
- Distinctive: line 27
Do not advance across a layer without pass evidence.
- Distinctive: line 28
If a downstream failure invalidates an upstream assumption, roll back minimally.
- Distinctive: line 29
Before closing, record touched layers, evidence, and final operation state.
- Distinctive: line 33
Use task tracking for multi-step work.
- Distinctive: line 34
Use agents only for broader searches or independent subtasks.
- Distinctive: line 35
Ask before irreversible or shared-state actions.
- Distinctive: line 36
Prefer the smallest layer re-entry during maintenance.
“Common” is measured: kept by at least 6 in 10 of the 24 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
Harness Engineering
Use the canonical skill body at:
SKILL.md
This file exists only as the Claude Code repository bridge. The authoritative workflow entry and surrounding normative sources are:
SKILL.mdcore/flow.mdcore/layer-details.mdcore/checklists.mdcore/exit-and-reentry.mdadapters/claude-code/host-map.mdadapters/claude-code/assembly.md
When executing inside Claude Code:
- Classify the request as
bootstrapormaintenance. - Select the smallest valid start layer using
core/flow.md. - Read only the canonical references required for the chosen scope.
- Do not advance across a layer without pass evidence.
- If a downstream failure invalidates an upstream assumption, roll back minimally.
- Before closing, record touched layers, evidence, and final operation state.
Operational notes:
- Use task tracking for multi-step work.
- Use agents only for broader searches or independent subtasks.
- Ask before irreversible or shared-state actions.
- Prefer the smallest layer re-entry during maintenance.
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.

