Individual skill

harness-engineering

Use when an agent workflow needs production-like runtime controls for context, tools, permissions, observability, scheduling, evaluation, recovery, or maintenance.

skills/harness-engineering/SKILL.md

Read pinned source

Source commit 5a645148a108d71c76521715117b737ae60b1423

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: Yes
Observed behavior: Local scripts
Last checked: Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 140
Repository last updated: Sep 19, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

claude-skills Repository topic
agentic Repository topic
ai-agents Repository topic
cursor-rules Repository topic
knowledge-management Repository topic
obsidian Repository topic
codex Repository topic
ontology Repository topic
loop Repository topic
loop-engineering Repository topic
engineering Derived category
operations Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 8,695 bytes
references/runtime-control-patterns.mddoc · 4,137 bytes
references/runtime-envelope-example.jsonasset · 1,869 bytes
references/runtime-envelope-plan.mddoc · 633 bytes
scripts/validate_runtime_envelope.pyruns · 12,780 bytes

Read excerpt


# Harness Engineering

<skill_contract>
  <input>An agent workflow, runtime environment, tools, data sensitivity, effects, cadence, risk, and operator constraints.</input>
  <output>An auditable runtime kernel with scoped permissions, scheduling, observability, recovery, and eval controls.</output>
  <done>An end-to-end trace and failure-path tests prove bounded, replayable, recoverable delegated action.</done>
  <non_goals>Business-task decomposition, prompt-only safety, broad credentials, or unbounded scheduled autonomy.</non_goals>

Treat the harness as the kernel around an LLM OS: context is RAM, durable state is disk, tools are system calls, skills are programs, the scheduler is control, and evals are verifiers. Load `references/runtime-control-patterns.md` for matrices and schemas. Start guarded automation from `references/runtime-envelope-example.json` and validate it with `scripts/validate_runtime_envelope.py --strict`.

## Usage Template

Provide: workflow, users, agent roles, environment, tools/connections, data sensitivity, delegated actions, cadence, throughput/SLA, failure history, and risk tolerance.