agent-harness-reference

agent-harness-reference is an Agent frameworks & building agents skill for AI agents, published by rjmurillo in the ai-agents repository on GitHub. Skillspace rates agent-harness-reference A (94/100) and it passed the safety scan; the rating is based on static analysis only.

Field reference for how Claude Code and GitHub Copilot CLI actually behave. Hook stdin protocol and exit semantics, plugin root env vars, Copilot payload casing and kill budget, dispatch and frontmatter contracts, plugin resolution, MCP layer. Contract rows cite evidence and mark docs-say vs empirically-verified. Use when you say `harness contract`, `copilot cli hook behavior`, `hook payload format`. Do NOT use for the portability campaign itself (use `ai-agents-portability-campaign`).

Grade
A
Quality
94 / 100
Safety
Passed
GitHub stars
38

Unproven: rated by static analysis only, not yet compared head-to-head.

Not launch-quality. It is graded A with a clean safety verdict, but our quality filters exclude it: a model that read it found it written only for the repository it lives in. So it is not in our launch-quality set, the skills our MCP server searches and recommends. How launch-quality is decided

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubrjmurillo/ai-agents

Our review

Architecture
100 / 100
Maturity
Packaged: licensed, with a version or references
Security scan
No issues found
License
MIT
Adoption
Adopted by 0 other repositories, in 0 collections
Scope
Repo-internal: written for the repository it lives in. Self-declared contributor-facing pack for this repo's own paths

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

More launch-quality Agent frameworks & building agents skills

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.