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 fmflurry/settings-opencode --skill setup-harnessgit clone --depth 1 https://github.com/fmflurry/settings-opencodeWrote 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/fmflurry/settings-opencode/setup-harness)<a href="https://agentmods.dev/skills/fmflurry/settings-opencode/setup-harness"><img src="https://agentmods.dev/badge/skills/fmflurry/settings-opencode/setup-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/fmflurry/settings-opencode/setup-harness"><img src="https://agentmods.dev/badge/skills/fmflurry/settings-opencode/setup-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 | $0.00025 | $0.01029 |
| Opus 5.5 | $0.00010 | $0.00412 |
| Sonnet 5.5 | $0.00005 | $0.00206 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade A, and why
setup-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 today.
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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup harness
Write one Cursor model per tier to both:
~/.cursor/rules/fmflurry-harness-models.mdc~/.agents/fmflurry-harness-models.md
Tiers
| Tier | Default slug | Fallbacks | Use | Agents |
|---|---|---|---|---|
| coding | grok-4.7-xhigh |
grok-4.7-xhigh -> grok-4.6-xhigh -> composer-2.5 |
implementation, tests, build fixes | coder, tdd-guide, build-error-resolver, refactor-cleaner, e2e-runner, api-spec-architect, gaudi |
| smart | grok-4.7-xhigh |
grok-4.7-xhigh -> grok-4.6-xhigh -> composer-2.5 |
planning, architecture, review, security; expensive, so dispatch it only when needed | planner, architect, code-reviewer, security-reviewer, angular-cop, dotnet-cop, database-reviewer, postgres-dba, gdpr-specialist, ecosystem-auditor, why-synthesizer |
| cheap | grok-4.7-medium |
grok-4.7-medium -> grok-4.6-medium -> composer-2.5 |
git, codebase search, docs, comment triage | git-specialist, scout, writer, doc-updater, why-investigator, comment-judge, haruspex-commentorum |
Allowed models
Only Cursor models: grok-4.7, grok-4.6, grok-4.5, and composer-2.5, with an optional effort suffix (max, xhigh, high, medium, low). Never third-party models. Never -fast variants. inherit and auto are allowed aliases: they run on the parent model and omit model.
If a slug is not in that set, ignore it and use the tier default. Log why: the slug, the tier, and that it is not a Cursor model.
Procedure
- Use these defaults. Do not pick a third-party slug even if one is advertised:
- coding:
grok-4.7-xhigh. Fallbacks:grok-4.7-xhigh->grok-4.6-xhigh->composer-2.5. - smart:
grok-4.7-xhigh. Fallbacks:grok-4.7-xhigh->grok-4.6-xhigh->composer-2.5. - cheap:
grok-4.7-medium. Fallbacks:grok-4.7-medium->grok-4.6-medium->composer-2.5. If the user asks for a different slug, accept it only when it is an allowed Cursor model orinherit/auto. Otherwise ignore it, keep the tier default, and log why.
- coding:
- Show the three slugs. Then write both files. Overwrite the tier lines so re-runs are idempotent. Keep custom lines that are not model assignments. If an existing tier line names a third-party or
-fastslug, replace it with the tier default and log why.
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.
- today Changed · +20 lines · -1 tokens per session 06c4b4b52a03
- 4d ago Changed · -25 lines · -1 tokens per session e528f1616f5d
- 8d ago First seen · 66 lines · 27 tokens per session scan A e3b447f07061
setup-harness is a skill published in the GitHub repository fmflurry/settings-opencode (171 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 1,029 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-08.
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…