harness-boundary SKILL.md skillA
harness-boundary from shimo4228/claude-harness is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add shimo4228/claude-harness/harness-boundary@git:20261008.b63e5f1Pins git:20261008.b63e5f1 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- shimo4228/claude-harness
- Path
skills/harness-boundary/SKILL.md- Versions recorded
- 8
- Latest version
- git:20261008.b63e5f1, committed Oct 8, 2026
- First version recorded
- Aug 21, 2026
- Size
- 9,362 bytes
- Repository stars
- 3
- License
- MIT
Design lens: which layer a harness mechanism belongs in, and whether it outlives the next model or runtime.
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
# harness-boundary — a design lens that treats as assets only what survives discarding the harness "The harness is the asset" is only half right. Harness logic that compensates for model-specific weaknesses goes stale with each model generation, and the runtime (tool execution, permissions, state, retry, agent loop) is being standardized and replaced. What remains are **other layers mixed into** the harness. This skill raises the questions for separating that mixture when a mechanism is added, changed, or reviewed. This is not an enforced architecture but a lens for judging asset boundaries, portability, and obsolescence. ## Core principles - Put model capability in the model. Do not reimplement it in the harness - Put procedural knowledge in skills - Keep values and responsibility boundaries explicit and inspectable - Put the definition of quality in evals - Put domain knowledge and history in data / memory - Keep the runtime as thin and swappable as practically possible And: **do not optimize to preserve the harness. Optimize to preserve what should survive swapping the harness.** When a new model makes existing logic unnecessary, that is not a design …
Read the whole file at its exact version.
How to install
mdr add shimo4228/claude-harness/harness-boundary@sha256:c2cb5447aa60e616The line at the top of this page pins the label git:20261008.b63e5f1, 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_f42t7wzjnredoxdn)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between Aug 21, 2026 and Oct 8, 2026, about one every 7 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261008.b63e5f1 latest | 2026-10-08 | b63e5f1 | 9,362 B | A | view · diff |
| git:20261008.7e591bd | 2026-10-08 | 7e591bd | 10,650 B | A | view · diff |
| git:20260926.538565e | 2026-09-26 | 538565e | 10,402 B | A | view · diff |
| git:20260919.f95d231 | 2026-09-19 | f95d231 | 10,141 B | A | view · diff |
| git:20260829.b4cb78e | 2026-08-29 | b4cb78e | 10,411 B | A | view · diff |
| git:20260825.494c03c | 2026-08-25 | 494c03c | 10,380 B | A | view · diff |
| git:20260825.985efb3 | 2026-08-25 | 985efb3 | 10,365 B | A | view · diff |
| git:20260821.eca6410 | 2026-08-21 | eca6410 | 10,342 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 (9362 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
shimo4228/claude-harness · 3 stars · license MIT · pushed 2026-10-18 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_f42t7wzjnredoxdn GET https://markdownregistry.com/api/v1/resolve?ref=shimo4228/claude-harness/harness-boundary GET https://markdownregistry.com/api/v1/blob/c2cb5447aa60e61645c751e9db7a0032044abf5201ac60d9bd39b675f7de9748
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.