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 evaluatorgit 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/evaluator)<a href="https://agentmods.dev/skills/random6913/claude-code-superkit/evaluator"><img src="https://agentmods.dev/badge/skills/random6913/claude-code-superkit/evaluator/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/evaluator"><img src="https://agentmods.dev/badge/skills/random6913/claude-code-superkit/evaluator.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 | $0.00035 | $0.01007 |
| Opus 5.5 | $0.00014 | $0.00403 |
| Sonnet 5.5 | $0.00007 | $0.00201 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
evaluator 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 yesterday.
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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluator
Determine whether implementation behavior meets the agreed contract. Use at the dev-orchestrator Evaluate gate or for requested post-implementation acceptance checks. Code style and unrelated improvements are outside this assessment.
Input and authority
Use the Sprint Contract or explicit criteria with MUST/SHOULD priorities, test methods, and thresholds; the changed scope; and, for a repeat pass, the prior report. Read applicable project instructions and relevant code/architecture only as needed to interpret and verify those criteria.
Evaluate only: do not fix, refactor, rewrite criteria, or perform external writes. Run authorized local checks with disposable output. Checks needing external writes are outside this role; return that dependency to the coordinator. Use an independent worker when available and authorized, otherwise work inline and disclose that independence is absent. Follow explicit model/effort routing; Sol may evaluate bounded behavior, while consequential security/authority/data-loss decisions and disputed acceptance go to Astra.
Evidence and scoring
Assess every criterion. Record one of:
- PASS: observed evidence meets the specified threshold.
- FAIL: observed behavior or implementation evidence contradicts the criterion. Cite the triggering input/path and actual result.
- UNVERIFIED: required evidence is unavailable, a check could not execute, or the criterion lacks a usable threshold. State what would resolve it; do not score missing evidence as zero.
- N/A: agreed scope makes the criterion inapplicable. Explain why. Do not silently remove a MUST requirement; uncertain applicability is UNVERIFIED until the contract owner resolves it.
Use numeric scores only when the contract requires them. Apply its anchors; for the dev-orchestrator default 0–10 scale, 7 means stated behavior is demonstrated, 5–6 means partial behavior with concrete gaps, 1–4 means substantial observed failure, and 0 means demonstrated absence. Higher scores require relevant evidence beyond the threshold, not unrelated features. UNVERIFIED and N/A have score N/A. A passing build alone does not prove application behavior or production readiness.
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.
- yesterday Changed · -76 lines · -6 tokens per session 496d34d9d840
- 1mo ago First seen · 140 lines · 41 tokens per session scan A e3c1ec81dbab
evaluator is a skill published in the GitHub repository RaNDoM6913/claude-code-superkit (3 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 1,007 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 2026-08-31.
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?".
find-weakness
Hypatia's targeted weakness-finding skill. Given a specific claim, architecture, or decision, finds the single strongest objection and the hidden assumption most likely to be wrong. Sharper and faster than critique-plan.
ai-dev-os-check
Checks code changes against AI Dev OS guidelines and automatically fixes violations. Based on benchmark Test 011: check+fix achieves +9.9 improvement vs report-only (+0.8). Supports git diff (default), branch comparison, and staged changes. Use --dry-run for report-only mode (no fixes applied).
ai-dev-os-scan
Scans ALL source files in the project against AI Dev OS guidelines. Unlike /ai-dev-os-check (which only checks git diff), this performs a full project-wide compliance scan. Use for initial audits, periodic full reviews, or after introducing new guidelines.
ai-dev-os-review
Performs a comprehensive self-review before creating a PR. Combines guideline compliance checking (L3) with design-level review (L2) and philosophical alignment (L1). Unlike /ai-dev-os-check which only checks rules, this also evaluates architecture decisions and code design quality.
ai-dev-os-extract
Extracts rules from the gap between AI-generated code and ideal code. Used after code review to add new rules to AI Dev OS guidelines. A Rule Harvesting approach to rule discovery.