agentleFS
Sign inStart free
manhquydevmanhquydev/flow-skill/skills/harness-skill/SKILL.md

harness

Skill9 starsChanged 28 days agoMITView on GitHub

Cổng durable harness cho flow projects (Claude Code + Codex). Prefer /flow harness (Python). Complete-only story status. Optional legacy harness-cli binary is archive-only. Kích hoạt khi cwd có flow project hoặc scripts/bin/harness-cli(.exe) hoặc user gõ /harness. Không code.

35 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use retro, verify and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AWSSkill

    retro

    Conduct a retrospective on a coding session.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    verify

    End-to-end app testing pipeline for browser-based web apps on cloud browsers via Azure Playwright Workspaces: verify the live app, author tests for working flows, heal failing tests, then re-run with video and produce one consolidated report. Three phases (app verification, test authoring, test healing) plus a scoped final sanity run; each phase emits a sub-report. Use when asked to "verify my app", "make sure my app works and has good test coverage", "do a full QA pass", "add tests where I'm missing coverage", "fix failing tests and add new ones", "smoke test before deploy", "QA my deployment", or any combined verify-and-test ask. Requires Azure CLI (`az login`) and a Playwright Workspace resource ID — bootstraps configs on first invocation. Browser-based web apps with Playwright only — not for unit/API tests, native mobile/desktop, load/perf, or full accessibility audits.

    Also in 3 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 4 projects that use this

  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 3 projects that use this

  • SentrySkill

    skill-creator

    Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 24 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Prefer flow projects: use /flow harness … (Python backend).

    line 22
  2. Very specific:

    If cwd has neither a flow project (.flow/ or flow/) nor scripts/bin/harness-cli / harness-cli.exe → early-exit (not a harness task).

    line 23
  3. Very specific:

    Read-only requests (explain, review, status) must not intake/trace/bootstrap.

    line 32
  4. Distinctive:

    Never forge shell verify pass from markdown alone.

    line 39
  5. Very specific:

    If using query sql on an archive binary: treat as read-only.

    line 43
  6. Very specific:

    If project uses /flow durable Python layer (.flow/harness.db with usage lineage):

    line 56
  7. Distinctive:

    Start task → intake + lane

    line 62

“Common” is measured: kept by at least 6 in 10 of the 24 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Harness — compliance gate (canonical in-repo)

Live authority: flow durable Python (/flow harness → skills/flow/harness/flow_harness.py)

  • mechanical flow.sh + semantic gate-rules.md.
    Historical: pre-EOL repository-harness protocol v1 is archive only (last published harness-cli-v0.1.22). See skills/flow/harness/GAP-MATRIX-0.1.17.md (SUPERSEDED).

Install optional copy to ~/.agents/skills/harness for global discovery; this file is the CI-tested source of truth under flow-skill/skills/harness-skill/.

Scope guard

  • Prefer flow projects: use /flow harness … (Python backend).
  • If cwd has neither a flow project (.flow/ or flow/) nor scripts/bin/harness-cli / harness-cli.exe → early-exit (not a harness task).
  • Non-dev questions → early-exit; do not force intake.

Before any mutation

  1. On flow projects: flow.sh harness query matrix (or /flow harness query matrix).
  2. Legacy archive binary (if present): optional harness-cli query contract --json — not required; not a live product pin.
  3. Read-only requests (explain, review, status) must not intake/trace/bootstrap.

Story status (trust)

  • Forbidden: story update --status implemented
  • Required: story complete with proof or flow-native
    story complete --id … --proof-source card_markdown_gate|manual|verify_command
  • Never forge shell verify pass from markdown alone.

SQL

  • If using query sql on an archive binary: treat as read-only. Mutating SQL is a trust violation.

Lane (FEATURE_INTAKE spirit)

Hard gates (auth, authz, data model, audit, external provider behavior, removing validation) → high_risk.
Scout files before classifying; draft → user confirm → CLI.

Trace

Match TRACE_SPEC tier to lane. Link --intake id. Honor-system: only outcome completed with real evidence.

Flow projects

If project uses /flow durable Python layer (.flow/harness.db with usage lineage):
do not set FLOW_HARNESS_BACKEND=rust — refuse-forward protects schema collision (009–012).
See skills/flow/harness/GAP-MATRIX-0.1.17.md.

Menu (empty invoke)

  • Start task → intake + lane
  • Complete task → story complete + trace
  • Decision / friction / status (query matrix)
  • Improve skill guidance → ritual R-IMPROVE-HARNESS (native-rituals.md)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free