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/waqas1412/claude-harnessWrote 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/waqas1412/claude-harness/harness)<a href="https://agentmods.dev/plugins/waqas1412/claude-harness/harness"><img src="https://agentmods.dev/badge/plugins/waqas1412/claude-harness/harness/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/waqas1412/claude-harness/harness"><img src="https://agentmods.dev/badge/plugins/waqas1412/claude-harness/harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
harness 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 1mo 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
{
"name": "harness",
"displayName": "Claude Harness",
"version": "0.8.0",
"description": "Portable read-only advisor agents, profile-driven PR/ticket skills, enforcement hooks, and a self-adapting /harness-init that tailors any repo to a documented index pattern.",
"author": {
"name": "Waqas Hameed",
"email": "[email protected]"
},
"homepage": "https://github.com/waqas1412/claude-harness",
"repository": "https://github.com/waqas1412/claude-harness",
"license": "MIT",
"keywords": [
"claude-code",
"claude",
"anthropic",
"agents",
"subagents",
"ai-agents",
"skills",
"slash-commands",
"hooks",
"code-review",
"developer-tools",
"productivity",
"orchestration",
"scaffolding",
"conventions",
"llm"
]
}
What it installs
The manifest is a name and a version. 9 skills, 17 agents, 2 hooks travel with it, and installing the plugin installs all of them — 986 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill harness-init A 31 tokens
- Skill workspace-init A 24 tokens
- Skill pr-comments A 52 tokens
- Skill sync-prs A 50 tokens
- Skill orchestrate A 50 tokens
- Skill refresh-seams A 25 tokens
- Skill ticket A 38 tokens
- Skill harness-distill A 47 tokens
- Skill pr A 50 tokens
- Agent spec-fidelity-auditor A 41 tokens
- Agent data-flow-timing-auditor A 47 tokens
- Agent design-principles-advisor A 36 tokens
- Agent developer-reviewer A 45 tokens
- Agent docs-researcher A 34 tokens
- Agent performance-optimizer A 31 tokens
- Agent system-architect A 33 tokens
- Agent system-designer A 28 tokens
- Agent accessibility-auditor A 44 tokens
- Agent compatibility-auditor A 43 tokens
- Agent security-auditor A 34 tokens
- Agent senior-software-engineer A 40 tokens
- Agent principles-engineer A 35 tokens
- Agent jira-ticket-author A 21 tokens
- Agent pr-author A 22 tokens
- Agent design-parity-auditor B 40 tokens
- Agent implementer C 45 tokens
- Hook PreToolUse A not measured
- Hook PostToolUse A not measured
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.
- 1mo ago Changed 4398c44b84e8
- 1mo ago First seen · 32 lines scan A 1232f505327b
harness is a plugin published in the GitHub repository waqas1412/claude-harness (2 stars, last pushed 12d ago), 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 2026-08-31.
Other plugins, from other repositories
fabrik marketplace
The Fabrik plugin marketplace — ambient awareness of Fabrik (a GitHub-Project-driven SDLC pipeline orchestrator) for your interactive Claude Code session.
fabrik
Ambient awareness of Fabrik (the GitHub-Project-driven SDLC pipeline orchestrator) for the human's interactive Claude Code session. Turns Claude into a product-management buddy and supervisor for projects that use Fabrik to automate issue processing.
fabrik-stages
SDLC stage workflow skills for the Fabrik pipeline orchestrator. Provides expertise for each pipeline stage: Specify, Research, Plan, Implement, Review, and Validate.
flutter-flame-harness
Idea-to-store harness for Flutter/Flame games: research (AI idea recommendation), plan, design, contract, generator-evaluator build loop, AdMob, build, screenshot, submit, retro.
agent-evaluation
Comprehensive evaluation framework for LLM agent systems. Multi-dimensional rubrics, LLM-as-judge with bias mitigation, pairwise comparison, direct scoring, confidence calibration, and continuous monitoring.
competitive-intelligence
Competitor analysis, market sizing, positioning maps, win/loss pattern synthesis, and battlecard creation for product and GTM decisions.