readme-audit

readme-audit is a command for Claude Code from Hulupeep/Specflow. It costs 0 tokens per session (905 once invoked), scanned A, original, MIT.

A command for reviewing a README as a guided path from a reader’s first question to a specific action they should take.

In plain words
What is it for?
Use it to assess a README’s sections, target readers, conversion goal, and links, producing a plan for a later rewrite.
Why use it?
It exposes missing information, poor section order, duplication, and unclear next steps before the README is rewritten.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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/hulupeep/specflow/readme-audit
Clone the repo
git clone --depth 1 https://github.com/Hulupeep/Specflow

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 readme-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/hulupeep/specflow/readme-audit.svg)](https://agentmods.dev/commands/hulupeep/specflow/readme-audit)
Your own site
<a href="https://agentmods.dev/commands/hulupeep/specflow/readme-audit"><img src="https://agentmods.dev/badge/commands/hulupeep/specflow/readme-audit.svg" alt="Measured on agentmods" height="20"></a>
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 905 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 5.1 $0.00000 $0.00905
Opus 5 $0.00000 $0.00452
Sonnet 5 $0.00000 $0.00181
Haiku 4.5 $0.00000 $0.00090

Measured 6d ago against content hash c745c585ea60, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

readme-audit 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 6d 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/readme-audit.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

README Audit

Audit a README's reading flow by treating it as a conversion funnel. Every section is evaluated against a target reader and a terminal action. Produces a structured audit blueprint that feeds directly into /readme-restructure.

Before Starting

Establish three things (ask if not provided):

  1. Target reader(s) — who arrives at the document? If two types, identify the conversion event (e.g. "evaluator becomes implementor")
  2. Terminal action — what should the reader be able to DO after reading? Must be concrete and specific.
  3. README path — which file to audit

Process

Step 1: Map the Document

Read the entire README. Create a section inventory: title, line range, one-sentence description. Flag any sections that duplicate content elsewhere in the document.

Step 2: Audit Each Section

For every section, produce a row:

# Section Lines Reader Q Answered Mental State IN → OUT Content Flow Classification

Reader Q Answered: What question is the reader asking when they arrive here? If it answers a question they haven't asked yet, it is mispositioned.

Mental State IN → OUT: Short phrase. E.g. "curious → convinced" or "ready to install → confused by options"

Content (0.0–1.0): Correct, appropriate density, right detail level for this reader at this moment?

Flow (0.0–1.0): Does this section hand the reader off cleanly to the next? Does the reader know where to go next and why?

Classification:

  • KEEP — right content, right location, right density
  • KEEP-SHORTEN — right location but too long; trim to one line with a link
  • PROMOTE — good content, wrong location; becomes its own linked doc
  • PROMOTE-MERGE — good content that should merge with another promoted section
  • REORDER — right content, wrong position in the flow
  • CUT — serves neither reader type at any position
  • DUPLICATE — repeats another section; one instance kept, rest cut

Read the full file on GitHub · 99 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. 6d ago First seen · 99 lines · 0 tokens per session scan A c745c585ea60

Subscribe to this mod's changes

readme-audit is a command published in the GitHub repository Hulupeep/Specflow (25 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 905 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 2026-08-30.