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.
npx skills add skillmds/skillmd --skill brave-mangit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skills/skillmds/skillmd/brave-man)<a href="https://agentmods.dev/skills/skillmds/skillmd/brave-man"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/brave-man/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/skills/skillmds/skillmd/brave-man"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/brave-man.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 | $0.00041 | $0.02410 |
| Opus 5.5 | $0.00016 | $0.00964 |
| Sonnet 5 | $0.00008 | $0.00482 |
| Haiku 4.5 | $0.00004 | $0.00241 |
Grade A, and why
brave-man 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 4d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brave Man
Overview
Most people describing a project ("vibe coders" included) only give a brief or partial picture of what they want. They can't be expected to specify everything up front — humans don't think in complete specs, and even when they try, they forget the small details that turn into real problems once the project has grown. If the agent starts building from a thin description, it fills the gaps with silent guesses, and by the time those guesses turn out wrong, they're expensive to undo.
Brave Man flips the order: clarify exhaustively first, build later. The agent's job here is NOT to write code, scaffold files, or produce an implementation plan. Its only job is to run a structured interview until the project is fully understood, then write that understanding down as a single, clean, self-contained prompt.md file that a fresh agent session can execute later.
When to Use This Skill
- Use when a user describes wanting to build a website, app, software, tool, or any kind of project.
- Use when the user request includes phrases like "build me a website", "I want an app for X", or "make a tool that does Y".
- Use BEFORE writing any code or implementation plan for a new build request.
Step-by-Step Guide
- Triage — a couple of quick questions to size up the project so question depth matches project complexity.
- Phased interview — work through the relevant phases below, one at a time, asking batched questions per phase.
- Track completion — maintain a visible checklist; don't move to synthesis until every relevant phase is closed (answered or explicitly defaulted).
- Synthesize — write the final
prompt.md. Do not generate an implementation plan artifact, scaffold a repo, or write any application code in this skill. - Hand off — tell the user to start a new chat, tag
prompt.md, and ask the agent to execute it.
Never skip straight to building because the request "sounded simple." Simple requests still go through triage — triage is what decides how short the interview gets, not whether it happens.
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.
- 4d ago First seen · 193 lines · 41 tokens per session scan A 5a566870ecff
brave-man is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 2,410 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-19.
Other skills, from other repositories
slopless
Use Slopless to review English Markdown for deterministic AI and human slop signals, including vague phrasing, formulaic prose, weak rhythm, filler, and cliches.
suiko
A Japanese writing and review workflow for checking whether text sounds uniform, translated, unnatural, or difficult to read. It supports writing and editing documents such as reports, guides, meeting notes, proposals, and emails.
poly-lint-and-format
Running poly lint / poly fmt — --fix, --format pretty|json|toon, --exclude, --config, exit codes, inline suppression, and the check → read-json → fix → re-check loop.
poly-orchestrator
Use poly as the single lint/format gate instead of invoking ruff/oxlint/rustfmt directly — one poly.toml, poly hooks install, poly migrate, CI via the Goldziher/poly setup Action.
poly-mcp
The poly MCP server — the eleven tools and which are read-only vs mutating, the paths/exclude/config/format params, async Tasks for the whole-project phase, and the isError contract.
poly-tiers-and-scope
Five mechanisms decide what actually inspects a file (crates/poly-core/src/registry.rs).