harness-engineering

1# Harness Engineering
2 
3Harness engineering designs the control system around an agent: what it may edit, how it receives feedback, where it writes state, how failures recover, and who can approve irreversible actions. The harness is the difference between a helpful agent session and an autonomous loop that can run for days without corrupting its objective.
4 
5## When to Activate
6 
7Activate this skill when:
8 
9- Building autonomous research or experimentation loops
10- Designing an agent environment with locked metrics and editable code or content
11- Creating PR-producing or background agents
12- Evaluating whether an agent can safely run without frequent human prompts
13- Adding novelty, ablation, pruning, rollback, or durable logging to an agent workflow
14- Preventing agents from gaming benchmarks, weakening rubrics, or losing state across compaction
15 
16Do not activate this skill for adjacent work owned by other skills:
17- General quality gates, regression suites, or outcome metrics without autonomous control surfaces: `evaluation`.
18- Tool schemas, response formats, and recovery errors for harness tools: `tool-design`.
19- Project-level task-model fit, pipeline shape, and cost planning: `project-development`.
20- Remote sandbox, warm-pool, and hosted session infrastructure: `hosted-agents`.
21 
22## Core Concepts
23 
24### Harness Boundary
25…