agent-harness-construction
agent harness construction
What it does
- Use micro-tools for high-risk operations (deploy, migration, permissions).
- Use medium tools for common edit/read/search loops.
- Use macro-tools only when round-trip overhead is the dominant cost.
- status: success|warning|error
- summary: one-line result
- nextactions: actionable follow-ups
- artifacts: file paths / IDs
Requirements & configuration
- 4. Compact at phase boundaries, not arbitrary token thresholds.
Derived from the skill's own SKILL.md documentation · extracted 2026-07-23
agent-harness-construction FAQ
What does the agent-harness-construction skill do?
Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use micro-tools for high-risk operations (deploy, migration, permissions). Use medium tools for common edit/read/search loops.
What does agent-harness-construction require?
4. Compact at phase boundaries, not arbitrary token thresholds.
How do I install agent-harness-construction?
Run: npx -y skills add https://github.com/affaan-m/everything-claude-code --skill agent-harness-construction --agent claude-code — the source lives at github.com/affaan-m/everything-claude-code.
Maintain agent-harness-construction?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/skills/affaan-m-everything-claude-code-agent-harness-construction?ref=badge) npx agentictools info skills/affaan-m-everything-claude-code-agent-harness-construction The second line is the CLI lookup for this page — handy in READMEs and docs.
