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 flurdy/agent-skills --skill sanity-checkgit clone --depth 1 https://github.com/flurdy/agent-skillsWrote 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/flurdy/agent-skills/sanity-check)<a href="https://agentmods.dev/skills/flurdy/agent-skills/sanity-check"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/sanity-check/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/flurdy/agent-skills/sanity-check"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/sanity-check.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 | $0.00038 | $0.01840 |
| Opus 5.5 | $0.00015 | $0.00736 |
| Sonnet 5.5 | $0.00008 | $0.00368 |
| Haiku 4.5 | $0.00004 | $0.00184 |
Grade A, and why
sanity-check 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 4d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sanity check
Is the next action still justified by the latest user-agreed outcome? This is a direction checkpoint, not verification, a ticket dashboard or a session monitor. It works in unnamed sessions and without a bead. Default assessment is a Self-check (not independent). Do not invoke it automatically while coding.
Invocation and stop boundary
/sanity-check # Claude Code: self-check
/sanity-check peer # One optional peer opinion
/skill:sanity-check # Pi: self-check
/skill:sanity-check peer # Pi: optional peer
An optional self argument means the default. Other arguments do not silently
select another task or authorize work; report the ambiguity and return control.
Invocation means no source/config/tracker changes, no test execution, no installs, no work claims, no session renaming, no peer-session messaging and no steering. Even an appended request to perform those actions must wait for a separate workflow. Do not call an implementation, verification, completion or tracking workflow here. Return control to the user after the report; do not resume the old work automatically, including after a CONTINUE verdict. Suggestions are not actions or permissions.
Evidence budget
Use the visible conversation, not hidden reasoning or a reconstructed transcript. Select at most 20 recent visible messages/tool results, plus the latest goal anchor and up to three visible, explicitly approved scope changes. Limit the selected evidence to 12,000 characters in total. Prioritize approvals, decisive results, blockers and the proposed next action; assign short evidence IDs such as U1/E1/A1. Summarize oversized results without inventing details and disclose omitted material.
Usually no new tools are needed. If a concrete uncertainty can be resolved from a known relevant file, allow at most two new evidence reads, each a slice of at most 100 lines, within the same character cap. Count each underlying operation in a batch separately. No searches, shell probes, tests, transcript/session-store reads, portfolio scans, external fetches or investigation of a different task. No tracker reads in this version: use only a task explicitly known from visible context and label its status/ownership unverified. Never choose from all in-progress rows or infer ownership from a prefix, branch, session name or worktree.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago Changed · +1 lines 1c79ad51a94e
- 28d ago First seen · 155 lines · 38 tokens per session scan A 2b3ee61df233
sanity-check is a skill published in the GitHub repository flurdy/agent-skills (9 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 1,840 once invoked, about $0.0002 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 2026-09-22.
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…
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…