plan-feature

plan-feature is a command for Claude Code from hackermanishackerman/claude-skills-vault. It costs 17 tokens per session (1,469 once invoked), scanned A, original, MIT.

A command for making an implementation plan for a software feature, with review from Claude and Gemini, two other AI systems.

In plain words
What is it for?
Use it when planning a production feature. It asks about the user problem, out-of-scope work, risk, and—when relevant—data, accessibility, security, dependencies, or performance.
Why use it?
It turns an unclear feature request into documented requirements, boundaries, risks, edge cases, and completion criteria before coding starts.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/hackermanishackerman/claude-skills-vault/plan-feature
Clone the repo
git clone --depth 1 https://github.com/hackermanishackerman/claude-skills-vault

Made for: Claude Code.

Wrote 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.

agentmods badge for plan-feature

README.md
[![agentmods](https://agentmods.dev/badge/commands/hackermanishackerman/claude-skills-vault/plan-feature.svg)](https://agentmods.dev/commands/hackermanishackerman/claude-skills-vault/plan-feature)
Your own site
<a href="https://agentmods.dev/commands/hackermanishackerman/claude-skills-vault/plan-feature"><img src="https://agentmods.dev/badge/commands/hackermanishackerman/claude-skills-vault/plan-feature.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,469 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.01469
Opus 5 $0.00009 $0.00734
Sonnet 5 $0.00003 $0.00294
Haiku 4.5 $0.00002 $0.00147

Measured 3d ago against content hash e9a88744a81d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

.claude/commands/plan-feature.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 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.

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?

Exit Criteria

Stop when: Requirements unambiguous, edge cases documented, success metrics defined.

Rule: Keep asking until EVERYTHING is clear. Never guess.

2. Research Phase

Codebase Archaeology

# Find similar patterns
Grep: "similar feature keywords"
Glob: affected file patterns
Read: existing architecture

External Research (if gaps)

  • Context7: Framework best practices
  • WebSearch: Latest docs, security advisories

Pre-Mortem

Before drafting, answer:

  • "If this fails in 6 months, what caused it?"
  • "What breaks at 10x scale?"

3. Plan Template (6 Sections)

# Feature: [Name]

## 1. Overview
- **Goal**: One-line summary
- **Success Metrics**: How we measure success
- **In Scope**: What we ARE building
- **Out of Scope**: What we are NOT building

## 2. Technical Design

### Architecture
[Component A] → [Component B] → [Component C]

### Data Model (if applicable)
- Schema changes
- Migration: Expand-Contract pattern (zero-downtime)

### Security (if applicable)
| Risk | Mitigation |
|------|------------|
| XSS | Input sanitization, CSP |
| Injection | Parameterized queries |

### Performance (if applicable)
- Caching strategy (TTL, invalidation)
- Query optimization (indexes, N+1)

## 3. Implementation

### Phase 1: Setup
- [ ] Feature flag
- [ ] Interfaces/contracts
- [ ] DB migration (additive only)

### Phase 2: Core
- [ ] Step 2.1: ...
- [ ] Step 2.2: ...

### Phase 3: Integration
- [ ] Step 3.1: ...
- [ ] Rollback checkpoint ←

## 4. Testing
| Type | Coverage | Focus |
|------|----------|-------|
| Unit | 80%+ | Core logic |
| Integration | APIs | Contracts |
| E2E | Critical paths | User flows |

## 5. Rollout & Observability
| Stage | % Users | Duration | Success Criteria |
|-------|---------|----------|------------------|
| Canary | 1% | 24h | Error <0.1% |
| Beta | 10% | 48h | P95 <Xms |
| GA | 100% | - | All green |

**Logs**: Key events | **Metrics**: Latency, errors | **Alerts**: Thresholds

## 6. Rollback Plan
1. Disable feature flag (instant)
2. Revert migration (if needed)
3. Restore cached data

Read the full file on GitHub · 208 lines

Changes

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.

  1. 3d ago First seen · 208 lines · 17 tokens per session scan A e9a88744a81d

Subscribe to this mod's changes

plan-feature is a command published in the GitHub repository hackermanishackerman/claude-skills-vault (2 stars, last pushed 5d ago), licensed MIT. It adds 17 tokens to every session and 1,469 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 2026-08-31.