agentic-harness
Skill0 starsChanged 6 months agoNo licenceView on GitHub
Protocol for synthesizing, debugging, iterating on, and verifying automated LLM pipeline harnesses (dark software factories, code-generation wrappers, multi-stage agentic systems). Think of it as the programmatic train station for agentic coding systems like OpenClaw, Claude Code, OpenCode, and GitHub Copilot CLI: they define the default backbone, while the harness routes work, enforces legality, tracks branch/story state, and reconciles failures into general harness fixes. Use when a harness produces incoherent output, illegal or prohibited actions, gate failures, LLM truncation bugs, test-generation failures, or violation-count divergence. The core contract: set a coherence=False todo at task start and iterate until you can flip it to True.
- Installs packages
- Commits and pushes
In this repository219 other files it gives its agents.
- agents/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- codex-agents/AGENTS.mdAGENTS.md
- memory-bank/AGENTS.mdAGENTS.md
- copilot-instructions.mdCopilot instructions
- .github/copilot-instructions.mdCopilot instructions
- active-inferenceSkill
- adapter-merging-strategiesSkill
- adjacent-surface-scanSkill
- agent-governanceSkill
- agentic-design-patternsSkill
- agentic-hyperparm-macdSkill
- agentic-hyperparmSkill
- agentic_kg_memorySkill
- agentic-orchestrationSkill
- agent-identitySkill
- agent-long-term-memorySkill
- ai-promptingSkill
- architectureSkill
- arxiv-bridgeSkill
- auto-ingestSkill
- auto-researchSkill
- autoresearchSkill
- axiom-ladder-searchSkill
- bitter-lessonSkill
- bm25-autoencoderSkill
- bm25-corpus-samplingSkill
- book-concept-distillationSkill
- bpe-bm25Skill
- build-observabilitySkill
- business-writingSkill
- causal-inferenceSkill
- cavemanSkill
- checklistSkill
- chrome-extensionsSkill
- class-balancingSkill
- claudeSkill
- cluster-quantized-knnSkill
- codebase-designSkill
- codebase-knowledge-graphSkill
- code-extractionSkill
- code-localizationSkill
- codemapSkill
- code-review-and-qualitySkill
- codeSkill
- cognitive-taxonomySkill
- comfyui-api-renderSkill
- concept-segmentationSkill
- consolidationSkill
- context-compactionSkill
- context-engineeringSkill
- context-graphSkill
- continual-learningSkill
- continuity-logSkill
- copula-manifold-samplerSkill
- create-steering-documentsSkill
- cross-hatch-samplingSkill
- crystallizationSkill
- ctp2-image-patchingSkill
- cua-desktop-agentSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
125 rules. About 0 are common, 104 are distinctive, and 21 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈104
Distinctive · estimate
This author's own choices. Worth a look.
21
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “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.
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.