Borrowing it
Nothing to install: this file belongs to sanmak/specops. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sanmak/specops/main/.claude/commands/readme.mdgit clone --depth 1 https://github.com/sanmak/specopsWrote 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/sanmak/specops/readme)<a href="https://agentmods.dev/commands/sanmak/specops/readme"><img src="https://agentmods.dev/badge/commands/sanmak/specops/readme/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/sanmak/specops/readme"><img src="https://agentmods.dev/badge/commands/sanmak/specops/readme.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 | $0.00000 | $0.01677 |
| Opus 5.5 | $0.00000 | $0.00671 |
| Sonnet 5.5 | $0.00000 | $0.00335 |
| Haiku 4.5 | $0.00000 | $0.00168 |
Grade A, and why
readme 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 1mo 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit and rewrite a project README for maximum clarity, value proposition, and developer conversion, using principles from Steve Jobs, David Ogilvy, Seth Godin, Simon Sinek, Paul Graham, George Orwell, and Jeff Bezos.
Instructions
Follow these steps precisely. This command evaluates a README against 8 dimensions drawn from marketing, writing, and open-source best practices, then generates a rewritten version optimized for the "star-or-bounce" moment.
Step 1: Read current README
Read README.md in the project root. If none exists, note "No README found" and switch to create mode (skip the scorecard, go directly to Step 4).
Also read any available project context: package.json, pyproject.toml, Cargo.toml, CLAUDE.md, or similar config files that reveal what the project does, its dependencies, and its target audience.
Step 2: Score against the README scorecard
Evaluate the current README on 8 dimensions. Each dimension is informed by a specific leader or pattern:
-
Hook (Steve Jobs, David Ogilvy): Does the first visible line name a problem or benefit? Not a feature description, not "A framework for X." The headline does 80% of the work. One big idea, not ten features.
-
Tagline (Steve Jobs): Is there a single sentence under 10 words that captures the core value? "1000 songs in your pocket" not "5GB hard drive with FireWire."
-
Problem statement (Simon Sinek): Does it articulate WHY this exists before WHAT it does? People don't care what you built until they feel the pain it solves. No product name in the first sentence of the problem.
-
Proof (Seth Godin): Is there a before/after, demo, screenshot, dogfood section, or usage example? Claims cost nothing. Evidence costs credibility. If it's remarkable, show it.
-
Getting started (Supabase/shadcn pattern): Can someone install and try it in under 5 minutes with 3 or fewer commands? If getting started requires reading docs first, it's too long.
-
Scanability (Paul Graham, George Orwell): Short sentences, tables over paragraphs, no jargon in the first 200 words. Write like you talk. Cut every word that does not change the meaning. Never use a long word where a short one will do.
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.
- 1mo ago First seen · 151 lines · 0 tokens per session scan A d77267551aac
readme is a command published in the GitHub repository sanmak/specops (49 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,677 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.
Other commands, from other repositories
skill-creator
Create or update an OpenCode skill using the bundled skill-creator workflow.
skill-registry
Rebuild the OpenCode skill registry for the current project and installed skills.
init-workspace-flow-questions
Phase 8 Questions of init-workspace-flow.
test-map
/test-map Generate full report for current project /test-map [path] Generate report for a specific directory /test-map --format=html Output as HTML file (default) /test-map --format=md Output as Markdown /test-map --open Generate HTML and open in browser (if tool available).
architect
You are a multi-role software architect. You operate through strict personas and a strictly-validated execution chain where each step is checked before the next. You give honest assessments, not flattery. You challenge every feature request for clarity, consistency, scalability, testability, and security. Your goal is…
generate
/generate jwt --sub user123 --role admin --exp 24h /generate jwt --alg RS256 --sub api-client --exp 7d /generate jwt --decode eyJhbGciOi... /generate keypair --alg RS256 /generate apikey --prefix sk /generate uuid --count 10 /generate password --length 32 /generate secret --length 64 --encoding base64 /generate hash…