Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/cboone/agent-harness-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/cboone/agent-harness-plugins/write-manual-verification-plan)<a href="https://agentmods.dev/plugins/cboone/agent-harness-plugins/write-manual-verification-plan"><img src="https://agentmods.dev/badge/plugins/cboone/agent-harness-plugins/write-manual-verification-plan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/cboone/agent-harness-plugins/write-manual-verification-plan"><img src="https://agentmods.dev/badge/plugins/cboone/agent-harness-plugins/write-manual-verification-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
write-manual-verification-plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"author": {
"name": "Christopher Boone"
},
"description": "Write a numbered, resumable checklist for checks run by hand, where every step says what to do, what you should see, and how to tell nothing from broken.",
"homepage": "https://github.com/cboone/agent-harness-plugins",
"keywords": ["checklists", "manual-testing", "planning", "resumable", "verification"],
"license": "MIT",
"name": "write-manual-verification-plan",
"repository": "https://github.com/cboone/agent-harness-plugins",
"skills": "./skills",
"version": "1.0.4"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 52 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago Changed cc384b1d62ea
- 8d ago Changed 372b88346a72
- 25d ago Changed 87e9d2f424b8
- 26d ago Changed 8cf2f4d7a545
- 1mo ago First seen · 14 lines scan A cab2de9a524e
write-manual-verification-plan is a plugin published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-16.
Other plugins, from other repositories
tdd-guard
Automated Test-Driven Development enforcement.
probity
TDD enforcement and guardrails for Claude Code, Codex, and GitHub Copilot CLI.
code-quality
Code quality pipeline — SOLID refactoring, TDD workflow, design patterns, performance optimization, and 6 specialist review agents.
sl
A five-team agent organization with enforced verification: hooks that block unverified test claims and fabricated imports, ship gates bound to content hashes, and an evidence ledger. Plain register by default; the lore is an optional overlay.
customgpt-claude-quadruple-verification
Quadruple verification for Claude Code — automatically blocks placeholder code, security vulnerabilities, and ensures output quality on every operation. Built by CustomGPT.ai for production teams.
tavs
Visual terminal state indicators for Claude Code sessions using OSC escape sequences. Changes background color and tab title based on Claude's state (processing, permission, idle, complete, compacting, subagent, toolerror).