Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/virgoC0der/awesome-claude-codenpx agentmods add skills/virgoc0der/awesome-claude-code/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/skills/virgoc0der/awesome-claude-code/harness)<a href="https://agentmods.dev/skills/virgoc0der/awesome-claude-code/harness"><img src="https://agentmods.dev/badge/skills/virgoc0der/awesome-claude-code/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/skills/virgoc0der/awesome-claude-code/harness"><img src="https://agentmods.dev/badge/skills/virgoc0der/awesome-claude-code/harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.02461 |
| Opus 5.5 | $0.00015 | $0.00984 |
| Sonnet 5.5 | $0.00007 | $0.00492 |
| Haiku 4.5 | $0.00004 | $0.00246 |
Grade A, and why
harness scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- smoke_url: <optional; HTTP endpoint to curl as health check> How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Engineering — Automated Development Pipeline
Launch a coordinated agent team to take a requirement from idea to verified, delivered code in any project.
Input: $ARGUMENTS — either a path to a requirement document, or a text description of what to build.
This skill is project-agnostic. It discovers the project's conventions at startup and uses them throughout — no language, framework, or domain is assumed.
Step 0: Bootstrap Project Context
Before spawning any agents, establish project context. The team must agree on how this project works so every agent uses the same commands and conventions.
0.1 Resolve project root
Use pwd (current working directory) as the project root unless the user supplied an explicit path. All later commands run relative to this root.
0.2 Load or create .harness/project.md
The framework reads project-specific configuration from .harness/project.md at the project root. This is the single source of truth shared by all agents.
ls .harness/project.md 2>/dev/null
If it exists: read it; pass its contents to every agent.
If it does not exist: do a one-shot detection pass and offer to create it:
- Detect language/build system from manifest files:
package.json/pnpm-lock.yaml/yarn.lock→ Node/JS/TSpyproject.toml/poetry.lock/requirements.txt/setup.py→ Pythongo.mod→ GoCargo.toml→ Rustpom.xml/build.gradle*→ JVMGemfile→ Rubycomposer.json→ PHPMakefile/justfile/Taskfile.yml→ custom recipes (read scripts directly)
- Inspect existing scripts (
package.jsonscripts,pyproject.toml[tool.*],Makefiletargets, etc.) to derive build/lint/format/test/run commands. - Read
CLAUDE.md,AGENTS.md,README.md, and anydocs/index for layer rules, file placement conventions, and domain knowledge sources. - Draft a
.harness/project.md(template below) and ask the user to confirm before writing.
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 First seen · 231 lines · 37 tokens per session scan A 021945ed380d
harness is a skill published in the GitHub repository virgoC0der/awesome-claude-code (1 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 2,461 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…