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 RaNDoM6913/claude-code-superkit --skill reality-checkergit clone --depth 1 https://github.com/RaNDoM6913/claude-code-superkitWrote 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/random6913/claude-code-superkit/reality-checker)<a href="https://agentmods.dev/skills/random6913/claude-code-superkit/reality-checker"><img src="https://agentmods.dev/badge/skills/random6913/claude-code-superkit/reality-checker/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/random6913/claude-code-superkit/reality-checker"><img src="https://agentmods.dev/badge/skills/random6913/claude-code-superkit/reality-checker.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 | $0.00042 | $0.00937 |
| Opus 5.5 | $0.00017 | $0.00375 |
| Sonnet 5.5 | $0.00008 | $0.00187 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
reality-checker 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reality Checker
Determine which completion claims are supported and what remains mandatory. Use for requested readiness assessment, a required delivery/release gate, or when a claimed outcome exceeds its evidence. Do not impose production deployment requirements on a local prototype or routine edit.
Input, context, and authority
Require the claimed outcome, agreed task/spec, intended environment, and supporting artifacts. Read applicable project requirements and only implementation/architecture needed to interpret those claims. If the meaning of "ready" is unspecified, identify the decision needed instead of inventing a production bar.
Assess only: do not edit implementation or criteria, deploy, modify external state, or expand the task. Authorized local checks may create disposable output. Follow explicit model/effort routing; Sol may collect and review bounded evidence, while Astra accepts consequential release, security, authority, data-loss, and irreversible decisions. Record missing acceptance as a gate, not implied approval. When no authorized independent worker is available, work inline and disclose self-review.
Evidence assessment
Evaluate each material claim as VERIFIED, FAILED, UNVERIFIED, or N/A with rationale tied to agreed scope. FAILED means observed contradiction. UNVERIFIED means insufficient evidence, an unexecuted check, or unavailable capability; it is not a measured defect or zero score. Do not remove mandatory criteria as N/A without a valid scope basis.
Select evidence for the claim:
- Behavioral claims need relevant implementation and execution evidence. Name whether it comes from fixtures, local integration, staging, or production; one does not prove the others.
- Test claims need command, target/environment, result, and relevant coverage of behavior. Coverage percentages or new-test counts are not universally required and do not prove correctness.
- Live API claims need traceable endpoint/environment, authorized request, and observed response. Redact credentials, cookies, tokens, and private data; never require full authenticated traffic in a report.
- UI/design claims may need rendered capture at the relevant viewport/state. Screenshots are not a universal backend acceptance requirement.
- Migration, performance, recovery, and security claims need checks appropriate to specific risks and promised guarantees. State their limits; do not promise exhaustive absence of regressions.
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 Changed · -59 lines · +12 tokens per session 76d2ab209e8d
- 1mo ago First seen · 121 lines · 30 tokens per session scan A bca1ad016cba
reality-checker is a skill published in the GitHub repository RaNDoM6913/claude-code-superkit (3 stars, last pushed 9d ago), licensed MIT. It adds 42 tokens to every session and 937 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 2026-09-03.
Other skills, from other repositories
Self-Review
Spawn a reviewer subagent with 4-6 specific verification questions before declaring non-trivial code work done. Triggers when changes are >30 LOC, multi-file, hot-path, prompt-affecting, or genuinely uncertain. Bad asks produce bad answers — this skill forces structured verification questions, not "is this good?".
remove-ai-slops
Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
visual-regression
Setup visual regression testing with Storybook stories, configuration, and CI/CD workflows. Supports Chromatic, Percy, BackstopJS. Auto-invoke when user says "set up visual regression", "add Chromatic tests", "add screenshot testing", or "set up Percy".
ln-32-test-strategy-planner
Plans risk-based test portfolios and acceptance evidence; does not write or execute tests.
ln-42-dependency-upgrader
Upgrades dependencies in reversible batches with version-specific compatibility and regression checks.