audit-plan

A command that reviews a feature plan like a product manager, using a scorecard, severity levels, duplicate checks, and suggested edits.

In plain words
What is it for?
Checking a plan's documents, progress, agent assignments, and possible duplicate features across plans.
Why use it?
It finds weaknesses and overlapping work before agents start implementing the plan.

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/paulbreuler/limps/audit-plan
Clone the repo
git clone --depth 1 https://github.com/paulbreuler/limps

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,249 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 $0.00000 $0.02249
Opus 5 $0.00000 $0.01125
Sonnet 5 $0.00000 $0.00450
Haiku 4.5 $0.00000 $0.00225

Measured 3d ago against content hash 23071a7920c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-plan 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/audit-plan.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Plan v1.0.0

Run a product-manager-style audit of a feature plan: scorecard by category, findings by severity, duplicate-feature detection across plans, and concrete next edits. Use after creating or updating a plan and before running agents; output is intended to feed back into the plan for iterative improvement.

Invocation

/audit-plan [plan-name-or-path]
/audit-plan --plan <plan-name>
/audit-plan --no-duplicates   # Skip cross-plan duplicate scan

MCP Integration

This command uses limps MCP tools for plan analysis:

  • Server: limps
  • Tools:
    • list_plans - List available plans (when no plan specified or plan not found)
    • list_agents - List agents for a plan (plan name required)
    • get_plan_status - Plan progress summary
    • process_doc - Read and analyze a single document (plan file, interfaces.md, README.md, agents, gotchas.md)
    • process_docs - Analyze multiple documents (e.g. all plan files for duplicate scan)
    • search_docs - Full-text search (optional, for keyword collisions in duplicate scan)

Usage: Call tools via call_mcp_tool with server: "limps" and the tool name. Paths are relative to configured docsPath (e.g. plans/NNNN-name/{plan-name}-plan.md).

When to Use

  • After /create-feature-plan or /update-feature-plan to validate plan quality before execution
  • Before /run-agent or assigning work to agents
  • When you want to check for overlapping features or plan intent across existing plans
  • When improving plans iteratively (audit output feeds into document edits)

Instructions for Claude

When this command is invoked, you must:

1. Identify the Plan

Use /limps-plan-operations identify-plan skill for consistent plan identification:

  • If user provides a plan name or path (e.g. 0041-limps-improvements or plans/0041-limps-improvements), use it.
  • If no plan provided: call list_plans (server: limps), then choose the most recently modified or highest-numbered plan as default, or ask the user which plan to audit.
  • Resolve to a plan directory name NNNN-descriptive-name and base path plans/NNNN-descriptive-name/.

Read the full file on GitHub · 179 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 · 179 lines · 0 tokens per session scan A 23071a7920c2

Subscribe to this mod's changes

audit-plan is a command published in the GitHub repository paulbreuler/limps (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,249 tokens. 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.