Skip to content
Agentmart
Submit a tool

harness-status

Restore state, health check, determine current phase, suggest next step

Skill by zxdxjtu

IndexedMIT★ 8
Write a review

Chalk Labs

Need help deploying harness-status?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/zxdxjtu-harness-status

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Restore state, health check, determine current phase, suggest next step

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/harness-status

What's inside

Skill name
harness-status
Description
Restore state, health check, determine current phase, suggest next step
License
MIT
Instructions
81 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Harness Status

Recover context and determine the current development phase.

## Step 1: Check Harness State

```bash
test -d .harness && echo "HARNESS_EXISTS" || echo "NO_HARNESS"
```

If no `.harness/` directory exists, tell the user to start with `/proposal`.

## Step 1.5: Check Configuration

```bash
test -f .harness/config.yaml && echo "CONFIG_EXISTS" || echo "NO_CONFIG"
```

If no config exists, suggest running `/harness-init` first for optimal experience.

## Step 2: Read State Files

1. List all specs: `ls .harness/specs/ 2>/dev/null`
2. Read config: Read `.harness/config.yaml` (if exists) for project context
3. Read tasks: Read `.harness/tasks.md` (if exists)
4. Read progress (last 50 lines): Read `.harness/progress.md` offset from end
5. Check sprint loop: Read `.harness/sprint-loop.md` (if exists)
6. Read pitfalls: Read `.harness/pitfalls.md` (if exists) — lightweight project pitfalls
7. Check invariants: Read `.harness/invariants.md` (if exists) for learned constraints
8. Check traces: Count events in `.harness/traces/events.jsonl` (if exists)
9. Recent git history: `git log --oneline -20`

## Step 3: Output Summary

For each feature, report:
- Spec status (draft/approved/tests-aligned)
- Test status (how many RED/GREEN)
- Task status (pending/in_progress/completed/failed counts per wave)
- Sprint loop status (active/inactive, iteration count)
- Pitfalls count (N known pitfalls recorded) — list them if ≤ 10, otherwise show count + categories

## Step 4: Determine Phase

| State | Current Phase | Next Step |
|-------|--------------|-----------|
| No specs | Phase 1 | `/proposal` |
| Spec approved, no tests | Phase 2 | `/tdd-align FXXX` |
| Tests exist, no task decomposition | Pre-Phase 3 | `/decompose FXXX` |
| Tasks decomposed, pending tasks exist | Phase 3 | `/sprint FXXX` |
| All tasks done, not verified | Phase 4 | `/verify FXXX` |
| Feature verified | Complete | Start next feature |

## Step 5: Health Check

- Dependencies installed? (`npm ci` / `pip install` / etc.)
- Build passes?
- Core tests green?
- If anything fails → **fix regression first**

## Step 6: Evolution Suggestions

Based on project state, suggest evolution actions:

| Condition | Suggestion |
|-----------|-----------|
| 3+ features completed, evolution log empty | "建议运行 `/harness evolve` 分析失败模式、发现可封装的重复工作" |
| No config.yaml | "建议运行 `/harness init` 适配项目规范" |
| Sprint had failures | "建议运行 `/harness evolve` 分析失败原因" |
| Eval scores trending down | "建议运行 `/adversarial-review` 深度审查" |

## Step 7: Output Plan

State clearly:
- Current phase
- Project configuration status (initialized? norms? invariants?)
- Specific goal for this session
- Which tasks/waves to work on
- Verification method
- Evolution status (invariants count, last evolution date)

From zxdxjtu/harness, MIT.

More from zxdxjtu/harness

Signals

Stars
8
Forks
3
Open issues
1
Last commit (this folder)
Apr 12, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from zxdxjtu

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get harness-status running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying harness-status?

CallGet help
Cite this page

harness-status skill. Agent Mart. https://agentmart.dev/skills/zxdxjtu-harness-status (last updated 2026-10-24)