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 quatico-solutions/agent-skills --skill reality-checkgit clone --depth 1 https://github.com/quatico-solutions/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/quatico-solutions/agent-skills/reality-check)<a href="https://agentmods.dev/skills/quatico-solutions/agent-skills/reality-check"><img src="https://agentmods.dev/badge/skills/quatico-solutions/agent-skills/reality-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/quatico-solutions/agent-skills/reality-check"><img src="https://agentmods.dev/badge/skills/quatico-solutions/agent-skills/reality-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 | $0.00080 | $0.01360 |
| Opus 5 | $0.00040 | $0.00680 |
| Sonnet 5 | $0.00016 | $0.00272 |
| Haiku 4.5 | $0.00008 | $0.00136 |
Grade A, and why
reality-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 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reality Check
Verify claims by trying to disprove them, with agents that did not make them.
Why this exists, and why it is not just "review it again"
An agent that inspects its own mechanism will usually conclude it works, because the mental model it uses to read is the same one it used to write. Reading code and judging it is not the same as running it and seeing what happens — only execution can contradict the model.
Two consequences shape everything below:
A green test suite proves only what it tests. A suite can be entirely green while the central mechanism is broken, if the untested case is precisely the one the mechanism exists for. When a claim matters, ask which test would fail if it were false; if the answer is none, the claim is unverified however many tests pass.
Checking your own work shares the blind spot that produced it. The useful instruction is not "confirm this" but "try to prove this is false." An agent asked "does this PR cover deliverable N?" pattern-matches its way to yes; one asked to refute it has to go and look.
When to run this
- Before claiming a piece of work is complete
- Before merging something whose failure would be expensive
- When a changelog or plan promises behaviour nobody executed
- After a fix — fixes are where regressions hide, and the fixer is the worst-placed person to find them
Not needed for work whose correctness is obvious on its face, or already covered by a test that would fail if the claim were false.
Steps
1. Collect the claims
From whatever states them: a plan's ## Changelog, a PR description, a
release checklist, or the user directly. Number them. A claim is a statement
that could be false — "the queue orders branches by wave" is a claim; "improved
the code" is not, and should be dropped rather than checked.
2. Establish the Definition of Done
Read it, do not assume it:
CLAUDE.md/AGENTS.md— look for a Definition of Done sectiondocs/definition-of-done.mdwhere the repo keeps onepackage.jsonscripts for the actual gate commands
What ships with it
1 file 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.
- 10d ago First seen · 127 lines · 80 tokens per session scan A c2994479058e
reality-check is a skill published in the GitHub repository quatico-solutions/agent-skills (2 stars, last pushed 6d ago), licensed MIT. It adds 80 tokens to every session and 1,360 once invoked, about $0.0004 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…