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.
git clone --depth 1 https://github.com/georgekhananaev/claude-skills-vaultWrote 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/commands/georgekhananaev/claude-skills-vault/plan-feature)<a href="https://agentmods.dev/commands/georgekhananaev/claude-skills-vault/plan-feature"><img src="https://agentmods.dev/badge/commands/georgekhananaev/claude-skills-vault/plan-feature/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/commands/georgekhananaev/claude-skills-vault/plan-feature"><img src="https://agentmods.dev/badge/commands/georgekhananaev/claude-skills-vault/plan-feature.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 | $0.00027 | $0.02941 |
| Opus 5 | $0.00014 | $0.01470 |
| Sonnet 5 | $0.00005 | $0.00588 |
| Haiku 4.5 | $0.00003 | $0.00294 |
Grade A, and why
plan-feature 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 11d 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 — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Feature Command
Trigger: /plan-feature only. Creates production-grade implementation plans with dual-AI validation.
Announce: "I'm using the plan-feature skill to create an implementation plan."
Output: Save plan to docs/plans/YYYY-MM-DD-<feature-name>.md
0. Pre-Check: Is the Idea Ready?
Before planning, assess if requirements are clear enough:
| Signal | Action |
|---|---|
| User says "I want to add..." with vague details | Use @brainstorm skill first to refine the idea |
| Multiple valid approaches, unclear trade-offs | Use @brainstorm to explore options |
| User isn't sure what they want | Use @brainstorm for collaborative discovery |
| Requirements are clear and specific | Proceed to Discovery Phase below |
Brainstorm produces: Design document at docs/plans/YYYY-MM-DD-<topic>-design.md
Plan-feature produces: Implementation plan with TDD tasks
Typical flow for new features: @brainstorm → /plan-feature → Execute
1. Discovery Phase (Adaptive)
Round 1: Core Questions (ALWAYS)
Use AskUserQuestion:
| Q# | Question | Header | Options |
|---|---|---|---|
| 1 | What user problem does this solve? | Problem | [Describe, Show existing code] |
| 2 | What's explicitly OUT of scope? | Anti-scope | [List exclusions, Nothing specific, Help define] |
| 3 | Risk level if this fails in prod? | Risk | [Critical, High, Medium, Low] |
Round 2: Adaptive Questions
Based on Round 1, ask ONLY relevant follow-ups:
| Trigger | Questions to Ask |
|---|---|
| DB likely (data/store/CRUD keywords) | Schema changes? Migration strategy? |
| Frontend (UI/page/component) | WCAG level? Design specs available? |
| Security-sensitive (Risk=Critical/High OR auth/payment/PII) | Compliance (SOC2/GDPR)? Security requirements? |
| New dependencies (library/integration/API) | Alternatives evaluated? Vendor lock-in? |
| Performance-critical | Latency budget? Expected load? |
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.
- 11d ago First seen · 340 lines · 27 tokens per session scan A f9d4ee38d664
plan-feature is a command published in the GitHub repository georgekhananaev/claude-skills-vault (28 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 2,941 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
test-skill
Test Claude Code skills using RED/GREEN/REFACTOR TDD phases in fresh subagents to prevent priming bias.
test-dotnet
Run .NET/C# tests for Unity projects and backend services.
test-rust
Run Rust tests for Solana programs and backend services.
test-ts
Run TypeScript tests for Solana frontends and Anchor programs.
test-and-fix
Run tests and automatically fix common issues.
benchmark
Benchmark CU usage and compare against baseline for regression detection.