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 mehrad-dm/mastermind --skill signaturegit clone --depth 1 https://github.com/mehrad-dm/mastermindWrote 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/mehrad-dm/mastermind/signature)<a href="https://agentmods.dev/skills/mehrad-dm/mastermind/signature"><img src="https://agentmods.dev/badge/skills/mehrad-dm/mastermind/signature/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/mehrad-dm/mastermind/signature"><img src="https://agentmods.dev/badge/skills/mehrad-dm/mastermind/signature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 13 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
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 | $0.00071 | $0.01216 |
| Opus 5 | $0.00036 | $0.00608 |
| Sonnet 5 | $0.00014 | $0.00243 |
| Haiku 4.5 | $0.00007 | $0.00122 |
Grade A, and why
signature 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 10d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Signature: capture a team's code style, turn it into rules the AI follows
A signature is your team's code style and conventions: the way your code recognizably looks and reads, like handwriting. The name is MasterMind's; the thing it captures is plain old code style.
A codebase has a real style that's rarely written down: people can't list their own conventions, but recognize a violation instantly. This skill surfaces that tacit style and makes it durable: a correction you give once becomes a permanent rule, not a repeated fix. Two phases: capture (private, in the quarantine), then distil (name-free, into a field pack).
The rule that never bends: patterns, not people. Describe what the code does ("this codebase resolves X by Y"), never rate a person ("so-and-so writes bad code"). The artifact is the pattern; the person is incidental: and a file that judges a named person is a career-risk if it leaks. Group by contributor only as a source of signal, phrased neutrally.
Phase 1: Capture (private, stays in the quarantine)
- Consent + Lab first. Ask before scanning a real, possibly-private codebase (and which paths). All
output has names, so it lands in
lab/(gitignored): if there's no Lab, set one up (quarantineskill) first. - Two sources, the second is the gold:
- Repeated corrections (highest value). What people tell the AI over and over: "do X not Y", "always…", "stop doing…", recurring review comments, AI diffs reverted-and-redone. Explicit, human-validated, de-noised. Weight by frequency (seen 20× = a rule; once = noise). Read the corrections log if one exists; help start one if not.
- Codebase patterns (lower confidence). Recurring idioms in code/history: naming, layout, how state/data/errors are handled. Candidate patterns, not truth (blame is noisy; in-repo ≠ endorsed).
- Output: neutral profiles in
lab/analysis/:pattern·frequency·source· first-passkind(convention | correctness | unsure). Neutral wording is not optional: if you can't phrase it about the pattern, drop it.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 69 lines · 0 tokens per session scan A 9184390e621c
signature is a skill published in the GitHub repository mehrad-dm/mastermind (24 stars, last pushed 10d ago), licensed MIT. It adds 71 tokens to every session and 1,216 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
writing-git-commits
Write clear, focused Git commit messages and keep commits easy to review.
st-full-workflow
Use when the user asks to run the complete end-to-end Strikethroo workflow for a work order in one shot in this repository — triggers include full workflow, end-to-end, plan and execute, do everything, run the whole strikethroo workflow. Do not use when the user wants only one stage (create a plan, generate tasks, or…
hatch3r-cli-toolbox
Category-indexed reference for 34 specialist CLI tools beyond the always-on five (ripgrep, jq, gh, fd, fzf). Use to pick the right tool for HTTP clients, ai-chat, structural-search, sed-style edits, data ops, browser automation, container ops, and more.
hatch3r-board-refresh
Regenerates the living board overview dashboard from current board state. Scans all open issues, computes health metrics, and updates the meta:board-overview issue.
hatch3r-qa-path
Produces a human-run manual QA test path from a PR, branch diff, or uncommitted working tree — a risk-ordered table of steps, expected results, and automated-coverage references plus a shippability sign-off. Rows are auto-proven via delegated verification sub-agents before emission, so the human walks only what…
hatch3r-recipe
Authors and validates composition specs that an orchestrating agent walks via the Task tool to run hatch3r commands and skills in a dependency-ordered sequence. Use when designing a multi-step capability composition, customizing an existing one, or debugging a composition the agent walks.