# 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.

- Skill: `aimasteracc/harness-preflight` (Agent Skill)
- Install (CLI): `npx skillmds@latest add aimasteracc/harness-preflight`
- Raw SKILL.md: https://api.skillmd.com/api/skills/aimasteracc/harness-preflight/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: aimasteracc (https://skillmd.com/u/aimasteracc)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/aimasteracc/harness-preflight

---


# 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

1. **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.