Skip to content
Agentmart
Submit a tool

setup-runtime-evidence-harness

Create or retrofit an agent instruction harness that enforces one runtime evidence path for acceptance.

Skill by btn0s

IndexedLicense unknown
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/btn0s-setup-runtime-evidence-harness

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Create or retrofit an agent instruction harness that enforces one runtime evidence path for acceptance. Use when Codex needs to set up AGENTS.md, .agents/rules, telemetry or evidence acceptance docs, scenario expectation templates, cross-agent instruction links, or project rules that prevent fake validation such as smoke tests, dependency checkers, pass/fail scripts, sidecar manifests, file-existence claims, or test-run success from replacing real runtime evidence. Useful for games, simulations, data pipelines, agents, product workflows, browser apps, services, robotics, and any project where acceptance must come from observed behavior rather than proxy checks.

Use cases: testing, data, agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/setup-runtime-evidence-harness

What's inside

Skill name
setup-runtime-evidence-harness
Description
Create or retrofit an agent instruction harness that enforces one runtime evidence path for acceptance. Use when Codex needs to set up AGENTS.md, .agents/rules, telemetry or evidence acceptance docs, scenario expectation templates, cross-agent instruction links, or project rules that prevent fake validation such as smoke tests, dependency checkers, pass/fail scripts, sidecar manifests, file-existence claims, or test-run success from replacing real runtime evidence. Useful for games, simulations, data pipelines, agents, product workflows, browser apps, services, robotics, and any project where acceptance must come from observed behavior rather than proxy checks.
License
unknown
Instructions
156 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (5)

  • SKILL.md
  • openai.yaml · agents/
  • file-blueprints.md · references/
  • intake-checklist.md · references/
  • scaffold_runtime_evidence_harness.py · scripts/

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from btn0s/agent-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jun 24, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
License unknown
Repository
github.com/btn0s/agent-skills
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from btn0s

Cite this page

setup-runtime-evidence-harness skill. Agent Mart. https://agentmart.dev/skills/btn0s-setup-runtime-evidence-harness (last updated 2026-10-24)