# Harness Readiness Dashboard

> MUST use before non-trivial review, merge, release, handoff, PR readiness, completion claims, progress assessment, maturity assessment, distance to target, roadmap gap, delivery gap, remaining modules, overall progress, 整体进展, 距离目标, 还差多少, 当前成熟度, 交付缺口, 功能模块缺口, ready 检查, 收尾前状态, 是否可以交付, 是否可以 review, 是否可以 handoff, 反复补丁, or 归零审视 when Codex needs a Harness readiness rollup without creating new artifacts.

- **Type:** Skill
- **Install:** `agentstack add skill-solitudetg-harness-coding-skills-harness-readiness-dashboard`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [solitudeTG](https://agentstack.voostack.com/s/solitudetg)
- **Installs:** 0
- **Category:** [Data & Analytics](https://agentstack.voostack.com/c/data-and-analytics)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [solitudeTG](https://github.com/solitudeTG)
- **Source:** https://github.com/solitudeTG/harness-coding-skills/tree/main/skills/harness-readiness-dashboard

## Install

```sh
agentstack add skill-solitudetg-harness-coding-skills-harness-readiness-dashboard
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Harness Readiness Dashboard

## Purpose

Answer one question:

```text
Can this work safely move forward, and what is still missing before the target state?
```

This is a status aggregation skill. It does not replace Start Gate, Vision Gate, Evidence, review, or knowledge capture, and it does not create official Feature, ADR, Lesson, or Evidence artifacts.

Use it for governance-oriented progress questions such as overall progress, distance to target, maturity, roadmap gap, delivery gap, or remaining modules. The dashboard should name the current stage, missing gates or evidence, and the smallest next action instead of inventing a percentage.

## Inputs

Gather only the smallest relevant set:

- Original request, Feature, spec, plan, or acceptance criteria.
- Latest Start Gate, Knowledge Retrieval, Vision Gate, review, and verification outputs if available.
- Evidence location or final verification commands.
- Bugfix attribution result and owning Feature Patch History for non-tiny bugfixes.
- Changed files, PR body, commit messages, or handoff note when present.
- ADR, Lesson, Backlog, or Feature status only when the current task may affect them.

If a source is missing, mark it as `missing`; do not invent status from memory.

## Core Rules

Use these status values:

```text
pass | missing | stale | not needed | pending | blocked
```

For `non-trivial` or `high-risk` work, mark `Delegation Gate` as `missing` when no explicit Delegation Gate decision is available.

Do not convert missing Delegation Gate evidence into self-review just because implementation is already finished. If delegation or independent review would have reduced risk but no explicit `single_agent`, `delegate`, or `blocked` decision exists, mark readiness as `conditional` or `blocked` and name the residual risk.

For non-tiny bugfixes, `Ready: yes` requires Bugfix Attribution to be `pass` or `not needed` with a reason. If an existing completed Feature owns the behavior and Patch History was not updated, readiness is `no` or `conditional`.

If a Feature has 3+ `## Patch History` rows or equivalent patch churn and no `## Patch Churn Review` is available, readiness must be `conditional` or `no`, not `yes`.

## Reference Map

Use references only when their trigger applies.

- `references/readiness-checks.md`: read when row-by-row readiness, reviewer policy, patch churn action, or the full output format is needed.

## Compact Output

```text
Harness Readiness Dashboard
Task class: tiny | routine | non-trivial | high-risk
Current stage: implementation | review | release | handoff | completion | progress
Evidence Level: quick | standard | exhaustive
Delegation Gate: single_agent | delegate | missing | blocked
Bugfix Attribution: pass | missing | ambiguous | not needed
Ready: yes | no | conditional
Blockers:
- ...
Next action:
- ...
```

Use `conditional` only when the work can proceed with explicitly named residual risk.

## Boundaries

- Do not create new documents from this skill; route to `harness-knowledge-capture`.
- Do not re-run Vision Gate here; report whether it exists and whether it is needed.
- Do not treat passing tests as product alignment; that belongs to Vision Gate.
- Do not treat a dashboard as Evidence; it only points to Evidence.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [solitudeTG](https://github.com/solitudeTG)
- **Source:** [solitudeTG/harness-coding-skills](https://github.com/solitudeTG/harness-coding-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-solitudetg-harness-coding-skills-harness-readiness-dashboard
- Seller: https://agentstack.voostack.com/s/solitudetg
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.