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 plan-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/plan-checker)<a href="https://agentmods.dev/skills/random6913/claude-code-superkit/plan-checker"><img src="https://agentmods.dev/badge/skills/random6913/claude-code-superkit/plan-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/plan-checker"><img src="https://agentmods.dev/badge/skills/random6913/claude-code-superkit/plan-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 | $0.00033 | $0.00776 |
| Opus 5.5 | $0.00013 | $0.00310 |
| Sonnet 5.5 | $0.00007 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
plan-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 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Checker
Determine whether proposed work can deliver the agreed outcome. Use at the dev-orchestrator Validate Plan gate or for requested plan validation. Do not turn ordinary implementation into a new planning requirement.
Input, context, and authority
Require the plan and requested outcome; include acceptance criteria, constraints, and allowed scope. Read applicable project instructions and referenced files/interfaces needed to check consequential assumptions. Load architecture documents selectively. Missing optional documentation is not itself a failure; a missing requirement needed to decide feasibility is a gap.
Review only. Do not rewrite the plan, implement fixes, or perform external writes. Authorized local checks may create disposable output. Follow explicit model/effort routing; consequential architecture, security, authority, data-loss, or irreversible decisions require Astra acceptance. If delegation is unavailable or unauthorized, review inline and state that this is not independent review.
Check what determines feasibility
- Map each requirement to planned work and an observable acceptance check. Identify omitted requirements and unrequested scope.
- Verify referenced files, symbols, APIs, and claims about current behavior. New files or directories are valid when their creation is planned; an absent parent is not automatically a defect.
- Check dependency order, compatibility, rollout/migration, and recovery where relevant. Separate technical dependencies from unavailable access or authorization.
- Assess whether tasks are concrete enough to implement and the complete scope can be reviewed. Recommend decomposition for coupling, risk, or uncertainty, not task/file-count thresholds.
- Check tests and documentation against actual behavior and project requirements. Require evidence appropriate to risk; do not add unrelated hardening or arbitrary coverage targets.
Reuse recorded command results only when bound to unchanged relevant code, inputs, and environment. Rerun for concrete uncertainty or relevant change. Cite repository facts with file/line or artifact references; identify unavailable evidence without inventing a defect.
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 · -44 lines · +9 tokens per session 78d90f29cdef
- 1mo ago First seen · 98 lines · 24 tokens per session scan A 650e5698fddd
plan-checker is a skill published in the GitHub repository RaNDoM6913/claude-code-superkit (3 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 776 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
nav-loop
Run tasks until complete with structured completion signals. Auto-invoke when user says "run until done", "keep going until complete", "iterate until finished", "loop mode", "autonomous mode".
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".
nav-diagnose
Detect quality drops in AI output and prompt re-anchoring. Auto-triggers after repeated corrections, context confusion, or when user says "something seems off", "you're not getting this".
git-commit
A guided Git commit workflow that examines changes and creates a commit message using the Conventional Commits format, a shared style for labeling changes such as features, fixes, tests, or documentation.
nav-compact
Clear conversation context while preserving knowledge via context marker. Use when user says "clear context", "start fresh", "done with this task", or when approaching token limits.
impeccable
Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics. Use when the user asks to build web components, pages, artifacts, posters, or applications, or when any design skill requires project context. Call with 'craft' for…