prompt-regression SKILL.md skillA
prompt-regression from chrono-meta/forge-harness is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add chrono-meta/forge-harness/prompt-regression@git:20261011.2279e9aPins git:20261011.2279e9a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- chrono-meta/forge-harness
- Path
plugins/fh-meta/skills/prompt-regression/SKILL.md- Versions recorded
- 6
- Latest version
- git:20261011.2279e9a, committed Oct 11, 2026
- First version recorded
- May 28, 2026
- Size
- 10,109 bytes
- Repository stars
- 31
- License
- MIT
Statically checks harness assets against a known-answer probe set after rule/skill changes — inspects the changed source for the trigger phrases, chain links and gate conditions each probe expects, and reports PASS/FAIL/SKIP per probe. Source inspection only; it does not run live sessions, so it catches assets that no longer SAY the right thing, not models that stop DOING it. Triggers on "prompt regression", "did my changes break anything", "regression check", "test harness changes".
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# prompt-regression — Harness Regression Detection After CLAUDE.md edits, rule changes, or new skill additions, harness behavior can silently regress. This skill runs a lightweight probe suite against the changed assets and compares outputs against saved baselines to surface regressions before they reach production. > **Scope distinction** > - harness-doctor: structural completeness (files, links, drift) > - prompt-regression: **behavioral correctness** — did the change alter expected AI response patterns? --- ## Triggers - `/prompt-regression` - "prompt regression", "regression check", "regression test" - "did my rule change break anything", "test harness changes", "verify harness behavior", "make sure my edit didn't change behavior" - After significant CLAUDE.md edits or new skill commits --- ## Execution Steps ### Step 1. Identify Changed Assets ```bash # What changed since last commit (or last N commits) git diff HEAD~1 --name-only -- CLAUDE.md .claude/ plugins/ ``` Classify each changed file: - `CLAUDE.md` → **core behavior** (high impact) - `.claude/rules/*.md` → **rule layer** (medium impact) - `plugins/*/skills/*/SKILL.md` → **skill behavior** (scoped impact) …
Read the whole file at its exact version.
How to install
mdr add chrono-meta/forge-harness/prompt-regression@sha256:94bb20d0ba4eab66The line at the top of this page pins the label git:20261011.2279e9a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_if2itrmk7x5soyic)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between May 28, 2026 and Oct 11, 2026, about one every 27 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261011.2279e9a latest | 2026-10-11 | 2279e9a | 10,109 B | A | view · diff |
| git:20260811.eede7ad | 2026-08-11 | eede7ad | 10,109 B | A | view · diff |
| git:20260803.c754718 | 2026-08-03 | c754718 | 6,759 B | A | view · diff |
| git:20260610.fa97770 | 2026-06-10 | fa97770 | 6,759 B | A | view · diff |
| git:20260603.4031ba1 | 2026-06-03 | 4031ba1 | 6,271 B | A | view · diff |
| git:20260528.ba592e2 | 2026-05-28 | ba592e2 | 6,030 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10109 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
chrono-meta/forge-harness · 31 stars · license MIT · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_if2itrmk7x5soyic GET https://markdownregistry.com/api/v1/resolve?ref=chrono-meta/forge-harness/prompt-regression GET https://markdownregistry.com/api/v1/blob/94bb20d0ba4eab66158d31a95f44a6d84ad2c5b0f3cfb2884c7607dfbe64cd8e
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from chrono-meta/forge-harness
Every file in chrono-meta/forge-harness