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.
npx skills add roarista/awesome-harness --skill awesomeharnessgit clone --depth 1 https://github.com/roarista/awesome-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/roarista/awesome-harness/awesomeharness)<a href="https://agentmods.dev/skills/roarista/awesome-harness/awesomeharness"><img src="https://agentmods.dev/badge/skills/roarista/awesome-harness/awesomeharness/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/roarista/awesome-harness/awesomeharness"><img src="https://agentmods.dev/badge/skills/roarista/awesome-harness/awesomeharness.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 | $0.00059 | $0.00539 |
| Opus 5 | $0.00030 | $0.00269 |
| Sonnet 5 | $0.00012 | $0.00108 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
awesomeharness 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
awesomeharness
Use this contract for the rest of the session. Read the repository's root CLAUDE.md when it is a compact project router, then STATE_CURRENT.md when present; do not routine-load historical STATE or archives.
Route
- Recall: targeted
ml search <term>or one domain prime. - Inventory: the injected
.codemap; do not reopen it wholesale. - Structure/reach: Graphify query/explain/path.
- Complete AST occurrences: Semgrep.
- Literal text, slices, history:
rg/ git. - Load specs, skills, MCPs, and plugins only when the task needs them.
Code loop
- State
GOAL / NOT-GOAL / DONE-WHEN / PROOF. - Prove
REUSE / ADAPT / REJECTagainst live files; stop if existing behavior covers the goal. - Decompose units as
CONTEXT / REUSE / CHANGE / GOAL / VERIFY. - For each non-trivial unit, launch one bounded builder, wait, then launch a distinct auditor against the same spec. Main-agent ability is not a reason to skip either launch. Never run sibling builders concurrently in a dirty checkout.
- Fix and re-audit until no high/critical finding remains; independently inspect the tree and verification output.
- Run the unit check, repository gate, and
check-all; claims require real output. - Commit scoped files, record durable learning in Mulch, update the repository's compact resume card, and push.
If subagents are unavailable, preserve the same separation sequentially: finish the spec, build, then re-read the diff with independent-auditor eyes.
Agent discipline
Every delegated prompt requires scoped reads and a complete report at .artifacts/agent-reports/<task>.md. Return only a decision-complete summary of at most eight lines with verdict, evidence, verification, risk, next action, and report path—never raw logs or diffs.
Non-negotiables
- Minimum code; no speculative abstractions or dependencies.
- Preserve unrelated dirty work; never force/reset/clean/stash/restore it away.
- No unauthorized spend, production mutation, messages, or destructive action.
- Keep progress terse and the final summary complete.
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.
- 10d ago First seen · 41 lines · 59 tokens per session scan A 4b411970978d
awesomeharness is a skill published in the GitHub repository roarista/awesome-harness (1 stars, last pushed 15d ago), licensed MIT. It adds 59 tokens to every session and 539 once invoked, about $0.0003 per session on Opus 5. 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…