harness-engineering SKILL.md skillA

harness-engineering from docxology/template is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add docxology/template/harness-engineering@git:20260713.397aa15

Pins git:20260713.397aa15 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
docxology/template
Path
.agents/skills/harness-engineering/SKILL.md
Versions recorded
1
Latest version
git:20260713.397aa15, committed Jul 13, 2026
Size
11,413 bytes
Repository stars
20
License
Apache-2.0

This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs, novelty gates, pruning, rollback, PR preparation, and human approval boundaries.

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

Harness engineering designs the control system around an agent: what it may edit, how it receives feedback, where it writes state, how failures recover, and who can approve irreversible actions. The harness is the difference between a helpful agent session and an autonomous loop that can run for days without corrupting its objective.

## When to Activate

Activate this skill when:

- Building autonomous research or experimentation loops
- Designing an agent environment with locked metrics and editable code or content
- Creating PR-producing or background agents
- Evaluating whether an agent can safely run without frequent human prompts
- Adding novelty, ablation, pruning, rollback, or durable logging to an agent workflow
- Preventing agents from gaming benchmarks, weakening rubrics, or losing state across compaction

Do not activate this skill for adjacent work owned by other skills:
- General quality gates, regression suites, or outcome metrics without autonomous control surfaces: `evaluation`.
- Tool schemas, response formats, and recovery errors for harness tools: `tool-design`.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add docxology/template/harness-engineering@sha256:dde3d8f46d4d09db

The line at the top of this page pins the label git:20260713.397aa15, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_amiglsvtoy3qiwq3.svg)](https://markdownregistry.com/a/art_amiglsvtoy3qiwq3)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jul 13, 2026.

versioncommittedcommitsizeaudit
git:20260713.397aa15 latest2026-07-13 397aa15 11,413 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (11413 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

GitHub

docxology/template · 20 stars · license Apache-2.0 · pushed 2026-10-31 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_amiglsvtoy3qiwq3
GET https://markdownregistry.com/api/v1/resolve?ref=docxology/template/harness-engineering
GET https://markdownregistry.com/api/v1/blob/dde3d8f46d4d09dbab41358baa3e8310d7fdfcd2fbefa127153ac4f6b5ef7b16

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 docxology/template

AGENTS.md@.agents AGENTS.md file
docxology/template · .agents/AGENTS.md
git:20261019.6b254e1 · audit A · 20 stars
AGENTS.md@.agents/skills AGENTS.md file
docxology/template · .agents/skills/AGENTS.md
git:20260829.b2727a9 · audit A · 20 stars
advanced-evaluation SKILL.md skill
docxology/template · .agents/skills/advanced-evaluation/SKILL.md · This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison…
git:20260713.397aa15 · audit A · 20 stars
bdi-mental-states SKILL.md skill
docxology/template · .agents/skills/bdi-mental-states/SKILL.md · This skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions…
git:20260713.397aa15 · audit A · 20 stars
context-compression SKILL.md skill
docxology/template · .agents/skills/context-compression/SKILL.md · This skill should be used when long-running agent sessions need context compression, structured summarization…
git:20260713.397aa15 · audit A · 20 stars
context-degradation SKILL.md skill
docxology/template · .agents/skills/context-degradation/SKILL.md · This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context…
git:20260713.397aa15 · audit A · 20 stars
context-fundamentals SKILL.md skill
docxology/template · .agents/skills/context-fundamentals/SKILL.md · This skill should be used to explain or reason about the foundational concepts of context engineering: what context is…
git:20260713.397aa15 · audit A · 20 stars
context-optimization SKILL.md skill
docxology/template · .agents/skills/context-optimization/SKILL.md · This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache…
git:20260713.397aa15 · audit A · 20 stars
evaluation SKILL.md skill
docxology/template · .agents/skills/evaluation/SKILL.md · This skill should be used when building agent evaluation systems: deterministic checks, regression suites…
git:20260713.397aa15 · audit A · 20 stars
filesystem-context SKILL.md skill
docxology/template · .agents/skills/filesystem-context/SKILL.md · This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading…
git:20260713.397aa15 · audit A · 20 stars
hosted-agents SKILL.md skill
docxology/template · .agents/skills/hosted-agents/SKILL.md · This skill should be used when designing hosted or background agent infrastructure: sandboxed execution, remote coding…
git:20260713.397aa15 · audit A · 20 stars
latent-briefing SKILL.md skill
docxology/template · .agents/skills/latent-briefing/SKILL.md · This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent"…
git:20260713.397aa15 · audit A · 20 stars

Every file in docxology/template

Other files named harness-engineering

harness-engineering SKILL.md skill
magnus919/agent-skills · harness-engineering/SKILL.md · Design, build, diagnose, and evolve agent harnesses: instructions, tools, execution environments, durable state…
git:20261031.20fddec · audit A · 162 stars
harness-engineering SKILL.md skill
habitat-thinking/ai-literacy-superpowers · ai-literacy-superpowers/skills/harness-engineering/SKILL.md · This skill should be used when the user asks about "harness engineering", "what is a harness", "harness framework", "AI…
git:20260414.89199fe · audit A · 119 stars

Browse by kind, by grade A, or by owner.