agent-harness skills

792 tagged agent-harness, measured the same way as everything else here.

Browse within: coding-agents 183skills 146claude-code-plugin 142harness-engineering 121ai-coding 116Autonomous Agents 104agentic-ai 104agentic-workflows 92agent-orchestration 82cli 79agent 68autonomous-agent 58local-first 57hooks 53

access-review

49

Rohit-ATS/Airlock

Skill Claude CodeCodex

How to compute what an access grant actually unlocks, rather than what its policy document says. Load before writing or reviewing any ACCESSGRANT change.

not rated 1 today A 33 tokens original MIT

reweave-operator

50

vnmoorthy/reweave

Skill Claude CodeCodex

Operate a Reweave self-healing web-data fleet — run pipelines, triage structural-drift incidents, review repair proposals, and manage the human approval workflow. Use whenever a monitored source is broken, a heal is pending, or the operator asks about pipeline health or impact.

not rated 0 10d ago A 62 tokens original MIT

coding-guardrails

51

frankxai/agentic-ops-hub

Skill Claude CodeCodex

Unified LLM coding rules, simplicity guidelines, surgical changes, and thinking protocols for all AI agents. Triggers on: code rules, guardrails, coding guidelines, coding conventions, coding style, surgical changes, goal-driven.

not rated 0 today A 50 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: