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 assessgit 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/assess)<a href="https://agentmods.dev/skills/mehrad-dm/mastermind/assess"><img src="https://agentmods.dev/badge/skills/mehrad-dm/mastermind/assess/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/assess"><img src="https://agentmods.dev/badge/skills/mehrad-dm/mastermind/assess.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 | $0.00108 | $0.00820 |
| Opus 5.5 | $0.00043 | $0.00328 |
| Sonnet 5.5 | $0.00022 | $0.00164 |
| Haiku 4.5 | $0.00011 | $0.00082 |
Grade A, and why
assess 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 15d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MasterMind: Assess
A documented "stop" is a good outcome. This decides whether an idea earns a spec, using evidence rather
than enthusiasm (~/.mastermind/engineering/core/product-sense.md). It works in a folder with no code.
Paths follow ~/.mastermind/engineering/core/spec-driven.md.
Idea: $ARGUMENTS.
Write one file, specs/ideas/<slug>.md, from specs/.templates/idea.md if present, else
template.md beside this file. Fill it stage by stage; each stage refines the same
file instead of producing a new one.
The five stages
- Intake. The idea in one sentence, who asked, and who it is for. Then the problem it removes, in
that person's words. An idea with no named person and no named problem stops here as
clarify. - Research. What exists today: the workaround people use, the competitors, the prior attempt in
this codebase. Search the code by the concept, not the request's wording, and read earlier verdicts in
specs/ideas/. An idea already built stops here with its path; one already stopped needs new evidence. Cite every claim with its source. Label each finding observed, reported or assumed. - Define. The outcome that would mean it worked, as one to three measurable signals with a target and a deadline. Then the constraints: budget, legal, technical, the constitution if one exists.
- Shape. The smallest version that would test the outcome. What it leaves out. The two or three assumptions it stands on, each with the cheapest test that could prove it false.
- Decide. One verdict, with its reasons and what would change it:
| Verdict | Means | Next |
|---|---|---|
| go | the evidence supports it and the smallest version is clear | hand the shaped version to specify |
| clarify | a named unknown decides it and can be resolved | the unknown, who resolves it, by when |
| stop | the evidence is against it, or the cost outweighs the outcome | the reason, and what would reopen it |
What ships with it
2 files 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.
- 15d ago First seen · 50 lines · 108 tokens per session scan A 3a7a9189ad10
assess is a skill published in the GitHub repository mehrad-dm/mastermind (23 stars, last pushed 6d ago), licensed MIT. It adds 108 tokens to every session and 820 once invoked, about $0.0004 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 2026-10-08.
Other skills, from other repositories
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…
code-sec-review
Static security review that hunts exploitable vulnerabilities, prioritizing unauthenticated and cross-tenant attack paths.
agent-decision
Deterministic self-evaluation rubric for decision escalations — scored every run using the FRAME framework.
code-quality-review
Reviews code and plans against the project's coding rules.
review-loop
Two-mode review loop — single reviewer per epic, three reviewers for full branch.
setup-new-acpx-key
Configure the API key (or other credential) for a registered ACPX agentid (claude/codex/cursor/gemini/qwen/copilot/pi/droid/iflow/kilocode/kimi/kiro/opencode/tlamatini) end-to-end across data.keys, config.json (top-level + acpx.agents. .env), regensecrets.py, and verification via acpdoctor.