An automated test runner for a previously prepared test plan that uses a web or desktop control tool to operate the live application. It records a verdict and evidence for each test step.

Execute planned browser or desktop tests, check preconditions, record step-by-step results, and distinguish machine evidence from decisions requiring human judgment.

It separates failed steps from steps that could not be run because a required condition was missing. This makes test results easier to attribute to the application or its setup.

qp-run — Skill for Claude Code by chrono-meta/forge-harness

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add chrono-meta/forge-harness --skill qp-run

Clone the repo

git clone --depth 1 https://github.com/chrono-meta/forge-harness

Made for: Claude Code.

Or install fh-qp, the plugin that ships this one along with the rest of its 4 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/chrono-meta/forge-harness/qp-run/github.svg)](https://agentmods.dev/skills/chrono-meta/forge-harness/qp-run)

Your own site

<a href="https://agentmods.dev/skills/chrono-meta/forge-harness/qp-run"><img src="https://agentmods.dev/badge/skills/chrono-meta/forge-harness/qp-run/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/chrono-meta/forge-harness/qp-run"><img src="https://agentmods.dev/badge/skills/chrono-meta/forge-harness/qp-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,261 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 6
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00121	$0.01261
Opus 5.5	$0.00048	$0.00504
Sonnet 5.5	$0.00024	$0.00252
Haiku 4.5	$0.00012	$0.00126

Measured 1mo ago against content hash c176a0e7d7e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

qp-run scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/fh-qp/skills/qp-run/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

qp-run — Automation (execute → verdict → mask)

Input: qp/plan/tcs.tsv + the adapter/engine lines from qp/plan/inventory.md. Output dir: qp/run/<YYYYMMDD-HHMM>/.

0. MTM state — decide once, write it first

#mtm: is the first line of verdicts.tsv:

value	when
`ACTIVE`	a plan document was given and you opened it (path recorded)
`UNAVAILABLE`	no plan document — expected values come from the inventory; the branch differs from plan is unreachable and the vocabulary collapses to AS_PLANNED / CODE_DIFFERS
`FAILED`	a plan document was given but could not be read — say so; do not fall back silently
`DISABLED`	the user turned it off (reason recorded)
`UNAVAILABLE` and `FAILED` are different events; never merge them.

1. Precondition first — attribution, not blocking

Before step 1 of each TC, establish its precondition. Navigation you can do (at:/about) you do; state you cannot create (logged-in, has-an-order) you mark UNMET_UNEXECUTABLE. A step-1 failure under an unmet precondition is BLOCKED, not FAIL — you never reached the screen, so it is not a claim about the app. Only step 1 is re-attributed; later steps failed after arrival.

2. Execute each step, observe before and after

web: accessibility snapshot before → action → snapshot after. desktop: screenshot before/after. Save each observation as <tc_id>_step<N>_{before,after}.{md,png} and append its stable id from bash plugins/fh-qp/scripts/qp_tools.sh screen-id <file> (a content hash — Playwright MCP ref tokens change every navigation, so a raw file hash is NOT stable; measured 2026-09-05) to evidence.tsv (tc_id<TAB>step<TAB>screen_hash) — this file is what qp-regress reads.

3. Verdict row per step — `verdicts.tsv` (7 tab-separated fields)

tc_id	status	branch	closure	verb	assertion	expected_source

status ∈ PASS FAIL BLOCKED AMBIGUOUS (AMBIGUOUS = could not map the step to one element: 0 candidates or a tie).
branch ∈ AS_PLANNED DIFFERS_FROM_PLAN CODE_DIFFERS NONE. DIFFERS_FROM_PLAN only under #mtm: ACTIVE and only with expected_source=PLAN_DOC. CODE_DIFFERS needs expected_source CODE or PLAN_DOC. NONE only for BLOCKED/AMBIGUOUS.
closure = MACHINE only if assertion names the check that closed it (text-visible:About, url==…, element-count==3). An empty assertion with MACHINE is invalid — that is the muscle-not-skeleton hole this field exists to close. Everything you decided by reading a screenshot is JUDGMENT.
Validate before you finish: bash plugins/fh-qp/scripts/qp_tools.sh mtm-check verdicts.tsv must print OK; run-verbs verdicts.tsv must print OK (≥1 click/input actually executed).

Read the full file on GitHub · 50 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 50 lines · 121 tokens per session scan A c176a0e7d7e0

Subscribe to this mod's changes

qp-run is a skill published in the GitHub repository chrono-meta/forge-harness (30 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 1,261 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.

Browser automation Claude Code E2E testing Multi-Agent Testing codex harness knowledge-management meta-harness

browser-qa

Drive a real headless browser against a locally-served web UI and capture screenshot evidence, reporting step-level PASS/FAIL/BLOCKED with extracted DOM text and console errors. Use when a phase on the docker QA image must exercise a rendered UI and attach screenshots — it complements the text-evidence verify/qa-test…

nearform/lastlight · 69 tokens

browser-inspect

Browser inspection and interaction for verifying rendered web UI during development.

ntorga/agent-starter-kit · 16 tokens

mstar-e2e

Separately requested E2E / real-browser / device / installed-deployment verification. Load only for an explicit request or amazing-e2e-check; never from routine QA or missing screenshots.

btspoony/mstar-harness · 46 tokens

evoflow-chat-smoke

An end-to-end check for the EvoFlow web chat: it can start or reuse a local Vite app, log in, create a conversation, send a chosen message, and check the displayed messages and reply. End-to-end testing checks a complete user flow rather than one small function.

EvovexAI/EvoFlow · 120 tokens

web-ui-test

Test the IronClaw web UI using the Claude for Chrome browser extension.

suyoumo/ClawProBench · 19 tokens

nobrainer-browser

Use when the owner says nb-browser or nobrainer-browser, asks to inspect or operate a rendered website, attach to an existing approved Chrome/Edge session, restart an approved non-default Chromium profile for loopback CDP, reproduce a browser flow, run Playwright tests, or record and analyze a Playwright trace. Prefer…

nobrainer-tech/nobrainer-tech-skills · 94 tokens