qp-regress

qp-regress is a skill for Claude Code from chrono-meta/forge-harness. It costs 115 tokens per session (828 once invoked), scanned A, original, MIT.

A regression check that reruns an earlier set of test cases without changing them, then compares each result with the earlier run. A regression is a new failure or behavior change caused by a later change.

In plain words
What is it for?
Use it to compare a new run with a baseline, report whether test cases left an entry screen, and record the result change for every case.
Why use it?
It prevents an overall pass rate from hiding failures in individual cases. It also distinguishes failures caused by a blocked or unmeasured environment from actual detections.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash plugins/fh-qp/scripts/qp_tools.sh surface-reach qp/run/<new-ts>/evidence.tsv.

Part of the fh-qp plugin — 4 skills shipped together

Good fit Use it to compare a new run with a baseline, report whether test cases left an entry screen, and record the result change for every case.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/chrono-meta/forge-harness
agentmods
npx agentmods add skills/chrono-meta/forge-harness/qp-regress

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.

agentmods badge for qp-regress

README.md
[![agentmods](https://agentmods.dev/badge/skills/chrono-meta/forge-harness/qp-regress/github.svg)](https://agentmods.dev/skills/chrono-meta/forge-harness/qp-regress)
Your own site
<a href="https://agentmods.dev/skills/chrono-meta/forge-harness/qp-regress"><img src="https://agentmods.dev/badge/skills/chrono-meta/forge-harness/qp-regress/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.

agentmods 80×15 button for qp-regress

Your own site · 80×15
<a href="https://agentmods.dev/skills/chrono-meta/forge-harness/qp-regress"><img src="https://agentmods.dev/badge/skills/chrono-meta/forge-harness/qp-regress.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 828 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00115 $0.00828
Opus 5 $0.00057 $0.00414
Sonnet 5 $0.00023 $0.00166
Haiku 4.5 $0.00012 $0.00083

Measured 6d ago against content hash 97527adae225, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

qp-regress 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 6d 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-regress/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

qp-regress — Regression (re-run unchanged → surface_reach → delta)

Input: a baseline qp/run/<ts>/ and the same qp/plan/tcs.tsv. Output: qp/regress/<ts>/.

1. Re-run unchanged

Execute the baseline's TCs with qp-run without editing them. Editing a TC to make it pass is a new run, not a regression — say so if the user asks for it.

2. surface_reach — did the batch leave the entry screen?

bash plugins/fh-qp/scripts/qp_tools.sh surface-reach qp/run/<new-ts>/evidence.tsv
result meaning
REACHED n/n every TC observed a screen other than the modal (entry) one
PARTIAL k/n some did — report which did not, by tc_id
NOT_REACHED 0/n the whole batch sat on one screen (a login wall, a dead env). Every FAIL in that run is unmeasured, not a detection — write that sentence in the report
UNMEASURED (rc 10) no evidence file / empty — not a zero
Denominator is all TCs, including ones that never executed; write surface_reach.txt with the raw line.

3. Per-TC delta — delta.tsv

tc_id	baseline_status	new_status	changed	note

One row per TC. changed=yes on any status change or on a same-status verdict whose closure moved from MACHINE to JUDGMENT (the check got weaker). A run where every row is changed=no may say "no regression"; a run reported only as "12 PASS both times" may not — the aggregate hides a swap.

4. Report — report.md

First 8 lines: target · engine/adapter/evidence · #mtm: state · surface_reach line · counts PASS/FAIL/BLOCKED/AMBIGUOUS new vs baseline · number of changed=yes · the sentence for NOT_REACHED if it applies · what was not measured (unexecuted TCs, dropped screenshots).

Done When

  1. surface_reach.txt holds a REACHED|PARTIAL|NOT_REACHED|UNMEASURED line produced by the tool · [mandatory-pass].
  2. delta.tsv has one row per TC in the baseline · [measured] — row count equals distinct tc_ids.
  3. A NOT_REACHED run's report contains the "FAILs are unmeasured" sentence · [measured] — grep.
  4. The delta's changed column reflects real behavior change, not selector drift · [judged — pairing: for each changed=yes, the before/after DOM snapshots are attached and a second session confirms the element moved, not the locator].

Read the full file on GitHub · 46 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.

  1. 6d ago First seen · 46 lines · 115 tokens per session scan A 97527adae225

Subscribe to this mod's changes

qp-regress is a skill published in the GitHub repository chrono-meta/forge-harness (14 stars, last pushed today), licensed MIT. It adds 115 tokens to every session and 828 once invoked, about $0.0006 per session on Opus 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.

Related

Other skills, from other repositories

taiyi-dev

A software-development stage that implements planned tasks using test-driven development, or TDD: write a failing test, make it pass, then improve the code. It checks the task plan, dependencies, file boundaries, and required completion evidence.

Dong90/oh-my-taiyiforge · 21 tokens

taiyi-test

A project workflow skill for verifying an implementation and producing a TEST.md record. TDD means writing a failing test, implementing the change, and then making the test pass; this skill checks that process and other regression cases.

Dong90/oh-my-taiyiforge · 24 tokens

harness-validate

Use when user invokes /harness-validate or wants to check whether a harness.yaml file is valid according to the Harness Protocol v1 JSON Schema. Reports validation errors with field paths and helpful fix suggestions.

harnessprotocol/harness-kit · 46 tokens

test-spec

BDD test specification generation from use case artifacts using Clark's (2018) UC2.0-to-Gherkin transformation algorithm. Transforms structured use case flows (basic flow, alternative flows, extensions) into Gherkin Feature files with Given-When-Then scenarios. Analyzes test coverage completeness against use case flow…

geekatron/jerry · 114 tokens

knowject-rag-eval

A skill for creating or reviewing evaluation cases for RAG, a system that searches stored documents before generating an answer, including the quality of its citations.

lynxlangya/knowject · 148 tokens

react-patterns

React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.

affaan-m/ECC · 49 tokens