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 goalgit 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/goal)<a href="https://agentmods.dev/skills/roarista/awesome-harness/goal"><img src="https://agentmods.dev/badge/skills/roarista/awesome-harness/goal/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/goal"><img src="https://agentmods.dev/badge/skills/roarista/awesome-harness/goal.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 | $0.00142 | $0.02291 |
| Opus 5 | $0.00071 | $0.01145 |
| Sonnet 5 | $0.00028 | $0.00458 |
| Haiku 4.5 | $0.00014 | $0.00229 |
Grade A, and why
goal 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 9d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
goal — design the loop, don't hand-prompt
The core truth from every loop-engineering source: the seed is everything. A loop runs hundreds of steps on the assumptions baked into the original spec. If the spec is vague, the loop doesn't make a bad assumption once — it makes the same one repeatedly and confidently, burning tokens at scale. So this skill spends almost all of its care up front: heavy planning, then maximal decomposition into a verifiable checklist. Only then does it loop. Prompting didn't die; it moved to the seed.
A loop is exactly five parts — all required: trigger + goal + verifier + stop condition + memory. Miss any one and you have either a hand-prompt or a runaway burn.
When NOT to loop (read first — this matters more than people think)
- No verifiable end-state. If you can't state a concrete check for "done," don't loop — you'll automate failure. Define the verifier first or do it by hand.
- One-shot / trivial work. A single edit doesn't need a loop's overhead.
- Live work mid-flight. Don't point a loop at a pipeline with an active session in the same working tree — you'll race it ([[concurrent-live-sessions-per-repo]]).
- Exploration where requirements are still forming. Loops need the end defined up front; if you're still discovering what you want, stay in the conversation.
Phase 1 — SEED (premium model; Ro stays in the loop)
This is 90% of the value. Do /plan-grade thinking and produce a durable seed doc on disk
(e.g. .planning/goals/<slug>.md, or repo-appropriate) so it survives compaction. The seed states:
- Objective + end-state — what is true when done, in plain language.
- Good vs bad output — concrete examples of a pass and a fail, so the verifier is unambiguous.
- Constraints / what not to break.
- The verifier — the independent, ideally mechanical check that proves done (test / script / hook / lighthouse / screenshot / judge model). Defined NOW, before any code.
- Stop conditions — goal met OR max iterations OR budget cap OR stall. No open-ended loops.
- Budget cap — a hard token/output ceiling. The romantic vision is you sleep while it works; the real job is making sure it stops. Set the cap here.
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.
- 9d ago First seen · 137 lines · 142 tokens per session scan A 4cce1c8ee369
goal is a skill published in the GitHub repository roarista/awesome-harness (1 stars, last pushed 14d ago), licensed MIT. It adds 142 tokens to every session and 2,291 once invoked, about $0.0007 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…