unhobble SKILL.md skillA
unhobble from broomva/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add broomva/skills/unhobble@git:20260729.596d3ddPins git:20260729.596d3dd in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- broomva/skills
- Path
skills/governance/unhobble/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260729.596d3dd, committed Jul 29, 2026
- First version recorded
- Jul 28, 2026
- Size
- 12,273 bytes
- Repository stars
- 5
- License
- MIT
Audit and rightsize a context surface — CLAUDE.md, AGENTS.md, a SKILL.md, a system prompt, or a single prompt — against the Claude-5 context-engineering reversals. Measures the surface (token budget, how much of it is phrased as hard rules vs judgment, near-duplicate sections, contradiction candidates, filesystem-derivable content, progressive-disclosure gaps), then adjudicates each section keep / relocate / delete using a grounding-aware predicate: prose backed by an independent mechanism is…
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
# unhobble Constraints written to protect against a weaker model's failure modes go net-negative once the model's judgement exceeds the rule. They collide with each other and with the user's actual request, and the model spends its reasoning resolving the collision instead of doing the work. The correction is deletion, not refinement. Anthropic's Claude Code team removed **over 80% of Claude Code's system prompt** for Claude 5 models with no measurable loss on their coding evals. The diagnostic that started it: reading their own transcripts, they found *"leave documentation as appropriate"* fighting *"DO NOT add comments"* inside a single request. This skill is that cut, made repeatable — and made safe, because the naive version of the rule deletes load-bearing prose. ## The measure-then-adjudicate split The script measures. It never says "delete." Whether a rule can go depends on whether something *other than the prose* enforces it — a hook, a CI job, a test, a runtime check. That is a grounding question, and a regex answering it would be guessing in a confident voice. So: ```bash python3 scripts/context_audit.py <path> [<path>...] --repo-root <repo> --budget 5000 …
Read the whole file at its exact version.
How to install
mdr add broomva/skills/unhobble@sha256:2cbbc2286ae3647aThe line at the top of this page pins the label git:20260729.596d3dd, 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_r4uoy6f3ahkaj4rz)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jul 28, 2026 and Jul 29, 2026, about one every day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260729.596d3dd latest | 2026-07-29 | 596d3dd | 12,273 B | A | view · diff |
| git:20260728.8710789 | 2026-07-28 | 8710789 | 11,061 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 (12273 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
broomva/skills · 5 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_r4uoy6f3ahkaj4rz GET https://markdownregistry.com/api/v1/resolve?ref=broomva/skills/unhobble GET https://markdownregistry.com/api/v1/blob/2cbbc2286ae3647a518dce6327a73e3a83ee766dca3659c3645a5d0bcd1cb18a
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.