harness-engineering SKILL.md skillA
harness-engineering from habitat-thinking/ai-literacy-superpowers is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add habitat-thinking/ai-literacy-superpowers/harness-engineering@git:20260414.89199fePins git:20260414.89199fe in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- habitat-thinking/ai-literacy-superpowers
- Path
ai-literacy-superpowers/skills/harness-engineering/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260414.89199fe, committed Apr 14, 2026
- First version recorded
- Apr 6, 2026
- Size
- 5,791 bytes
- Repository stars
- 121
- License
- a license file GitHub does not identify
This skill should be used when the user asks about "harness engineering", "what is a harness", "harness framework", "AI code quality", "context engineering", "architectural constraints", "garbage collection for code", or wants to understand the conceptual foundation behind the harness-engineering plugin.
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 Engineering A harness is the combined set of deterministic tooling and LLM-based agents that keeps AI code generation trustworthy and maintainable at scale. The concept originates from Birgitta Boeckeler's article "Harness Engineering" (2026), which identifies three components that together form a complete harness. For the full article summary and four hypotheses, consult `references/boeckeler-summary.md`. ## The Three Components ### Context Engineering The knowledge an LLM needs to work effectively in a codebase. This includes explicit documentation (conventions, constraints, stack declarations) and implicit context (the code design itself). A well-structured codebase is easier to harness than a sprawling one because the structure communicates intent. In this plugin, context engineering lives in HARNESS.md's **Context** section — stack declaration, convention documentation, and any project-specific knowledge that shapes how code should be written. ### Architectural Constraints Rules that must be enforced — not suggestions, but hard boundaries. Each constraint is backed by a **verification slot** that can be filled …
Read the whole file at its exact version.
How to install
mdr add habitat-thinking/ai-literacy-superpowers/harness-engineering@sha256:12b5785979500e7fThe line at the top of this page pins the label git:20260414.89199fe, 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_b66huxv6ywujga4y)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Apr 6, 2026 and Apr 14, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260414.89199fe latest | 2026-04-14 | 89199fe | 5,791 B | A | view · diff |
| git:20260406.60a61ca | 2026-04-06 | 60a61ca | 4,249 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 (5791 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
habitat-thinking/ai-literacy-superpowers · 121 stars · license a license file GitHub does not identify · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_b66huxv6ywujga4y GET https://markdownregistry.com/api/v1/resolve?ref=habitat-thinking/ai-literacy-superpowers/harness-engineering GET https://markdownregistry.com/api/v1/blob/12b5785979500e7f564614de10e234392c76807e0f2ee463e3b6c442d0a56a33
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 habitat-thinking/ai-literacy-superpowers
Every file in habitat-thinking/ai-literacy-superpowers