measurement-campaign SKILL.md skillA
measurement-campaign from sshadows/lethal is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add sshadows/lethal/measurement-campaign@git:20261021.98334d7Pins git:20261021.98334d7 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- sshadows/lethal
- Path
.claude/skills/measurement-campaign/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261021.98334d7, committed Oct 21, 2026
- First version recorded
- Aug 6, 2026
- Size
- 17,740 bytes
- Repository stars
- 10
- License
- MIT
Use when running LethAL against a real project or customer app, measuring a real codebase's suite, comparing two live runs, or writing a pre-commitment for any of those. Drives live, billed environments.
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
# Running a measurement campaign A campaign is a sequence of live runs whose numbers are meant to be believed months later. What makes a number believable is not the run — it is what was written down before it. ## The mistake to expect The 2026-08-03 campaign (`docs/campaign/2026-08-03-do/` — a preflight stage plus three measured stages, records committed per stage) followed CLAUDE.md throughout — every fix red-checked, every gate per-mutant rather than aggregate — **and still made two errors.** It pre-committed the wrong QUANTITY as its expected mutant count, and it silently dropped a gate between stages. Both became visible as errors rather than as results, and both were caught by rules that are nowhere in CLAUDE.md. > That campaign named its stages `rung0`, `rung1`, `rung2`, `rung3`, and its committed records still > carry those names on disk. This page says "stage 1/2/3" for the same things — a stage name is > whatever the campaign author picked, and `--stage rung1` still resolves those exact files. That is the argument for this skill. CLAUDE.md governs **code changes**: prove the fix is …
Read the whole file at its exact version.
How to install
mdr add sshadows/lethal/measurement-campaign@sha256:c2827f2d497b63bdThe line at the top of this page pins the label git:20261021.98334d7, 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_2j672sy46toiazhf)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Aug 6, 2026 and Oct 21, 2026, about one every 19 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261021.98334d7 latest | 2026-10-21 | 98334d7 | 17,740 B | A | view · diff |
| git:20261004.4805843 | 2026-10-04 | 4805843 | 17,350 B | A | view · diff |
| git:20260806.2aff6a9 | 2026-08-06 | 2aff6a9 | 16,921 B | A | view · diff |
| git:20260806.2762117 | 2026-08-06 | 2762117 | 16,595 B | A | view · diff |
| git:20260806.d5ddff6 | 2026-08-06 | d5ddff6 | 15,809 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 (17740 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
sshadows/lethal · 10 stars · license MIT · pushed 2026-11-07 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_2j672sy46toiazhf GET https://markdownregistry.com/api/v1/resolve?ref=sshadows/lethal/measurement-campaign GET https://markdownregistry.com/api/v1/blob/c2827f2d497b63bddb504d453d77ff4e148354b6277b2393bb742a1a4666cf2d
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.