How do I install the Harness Preflight skill?

Run npx skillmds@latest add aimasteracc/harness-preflight in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Harness Preflight safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Harness Preflight?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Harness Preflight free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Harness Preflight?

aimasteracc (@aimasteracc) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Harness Preflight by aimasteracc — Agent Skill

Name: Harness Preflight
Author: aimasteracc

Harness Preflight

Run an interactive pre-flight checklist before launching a long autonomous agent run, so the harness is sound before you hand it hours of work. Use when the user says "pre-flight", "ready to run autonomously?", "harness check", or right before kicking off an unattended/overnight task.

aimasteracc 0bd23e4 3.1 KB Updated Sep 17, 2026

File contents

harness-preflight — Don't launch a long run on a harness you haven't checked

Purpose

A long autonomous run amplifies whatever you start it with. A missing "done" condition, an ungated plan, or no checkpoint mechanism turns into hours of confidently-wrong work. This skill walks the seven pre-conditions a sound harness needs and refuses to green-light until the gaps are named. It's the seatbelt check before the autonomous drive.

How to run

Walk each item. For each: OK (with the evidence) or GAP (with what's missing and the quickest fix). End with a single go/no-go verdict. Don't rubber-stamp — a GAP on items 1, 2, or 4 is a no-go.

The checklist

Observable definition of done. Is "done" a command that passes or a state you can see — not a vibe? → If no: define it now (delegate to thinking about the user-visible success state).
Decomposition exists. Is the work broken into discrete, independently verifiable units — not one giant "implement it" step? → If no: decompose first (guards against one-shot impulse).
Generation ≠ certification. Is there an independent grader — tests, a type-checker, a separate review pass — so the agent isn't certifying its own output? → If no: wire one in.
Upstream gate. Is the high-leverage upstream artifact (plan/spec/schema) validated before dependent work fans out? → If no: add a checkpoint right after it (guards against spec cascade).
Checkpoint / handoff mechanism. Can state survive a context reset — is there a place the agent writes progress, so nearing the limit triggers a save, not a panic? → If no: set up a .handoff/ convention (see the context-handoff skill).
Constraints are loaded. Does a CLAUDE.md (or equivalent) state the NEVERs — the actions that cause real damage? → If no: generate one (see claude-md-architect).
Blast radius is bounded. If the run goes wrong, what's the worst it can touch? Is it on a branch / sandbox / with no deploy or destructive perms? → If no: bound it before launching.

Verdict format

## Harness Pre-Flight — <task>

1. Done condition ........ OK | GAP: <fix>
2. Decomposition ......... OK | GAP: <fix>
3. Independent grader .... OK | GAP: <fix>
4. Upstream gate ......... OK | GAP: <fix>
5. Checkpoint/handoff .... OK | GAP: <fix>
6. Constraints loaded .... OK | GAP: <fix>
7. Blast radius bounded .. OK | GAP: <fix>

VERDICT: GO | NO-GO — <one line. NO-GO if any of 1, 2, 4, 7 is a GAP.>

Notes

This skill composes the rest of the kit: gaps route to claude-md-architect (item 6), context-handoff (item 5), and the fixes in failure-mode-audit (items 1–4).
A 60-second pre-flight routinely saves hours of an autonomous run spent building the wrong thing soundly.

---name: harness-preflightdescription: Run an interactive pre-flight checklist before launching a long autonomous agent run, so the harness is sound before you hand it hours of work. Use when the user says "pre-flight", "ready to run autonomously?", "harness check", or right before kicking off an unattended/overnight task.---# harness-preflight — Don't launch a long run on a harness you haven't checked## PurposeA long autonomous run amplifies whatever you start it with. A missing "done" condition, anungated plan, or no checkpoint mechanism turns into hours of confidently-wrong work. Thisskill walks the seven pre-conditions a sound harness needs and refuses to green-light untilthe gaps are named. It's the seatbelt check before the autonomous drive.## How to runWalk each item. For each: `OK` (with the evidence) or `GAP` (with what's missing and thequickest fix). End with a single go/no-go verdict. Don't rubber-stamp — a GAP on items 1, 2,or 4 is a no-go.## The checklist1. **Observable definition of done.** Is "done" a command that passes or a state you can see — not a vibe? → If no: define it now (delegate to thinking about the user-visible success state).2. **Decomposition exists.** Is the work broken into discrete, independently verifiable units — not one giant "implement it" step? → If no: decompose first (guards against one-shot impulse).3. **Generation ≠ certification.** Is there an independent grader — tests, a type-checker, a separate review pass — so the agent isn't certifying its own output? → If no: wire one in.4. **Upstream gate.** Is the high-leverage upstream artifact (plan/spec/schema) validated before dependent work fans out? → If no: add a checkpoint right after it (guards against spec cascade).5. **Checkpoint / handoff mechanism.** Can state survive a context reset — is there a place the agent writes progress, so nearing the limit triggers a save, not a panic? → If no: set up a `.handoff/` convention (see the `context-handoff` skill).6. **Constraints are loaded.** Does a CLAUDE.md (or equivalent) state the NEVERs — the actions that cause real damage? → If no: generate one (see `claude-md-architect`).7. **Blast radius is bounded.** If the run goes wrong, what's the worst it can touch? Is it on a branch / sandbox / with no deploy or destructive perms? → If no: bound it before launching.## Verdict format```## Harness Pre-Flight — <task>1. Done condition ........ OK | GAP: <fix>2. Decomposition ......... OK | GAP: <fix>3. Independent grader .... OK | GAP: <fix>4. Upstream gate ......... OK | GAP: <fix>5. Checkpoint/handoff .... OK | GAP: <fix>6. Constraints loaded .... OK | GAP: <fix>7. Blast radius bounded .. OK | GAP: <fix>VERDICT: GO | NO-GO — <one line. NO-GO if any of 1, 2, 4, 7 is a GAP.>```## Notes- This skill composes the rest of the kit: gaps route to `claude-md-architect` (item 6), `context-handoff` (item 5), and the fixes in `failure-mode-audit` (items 1–4).- A 60-second pre-flight routinely saves hours of an autonomous run spent building the wrong thing soundly.

Frequently asked questions