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 analyzegit 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/analyze)<a href="https://agentmods.dev/skills/mehrad-dm/mastermind/analyze"><img src="https://agentmods.dev/badge/skills/mehrad-dm/mastermind/analyze/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/analyze"><img src="https://agentmods.dev/badge/skills/mehrad-dm/mastermind/analyze.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 | $0.00098 | $0.00972 |
| Opus 5.5 | $0.00039 | $0.00389 |
| Sonnet 5.5 | $0.00020 | $0.00194 |
| Haiku 4.5 | $0.00010 | $0.00097 |
Grade A, and why
analyze 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MasterMind: Analyze
A read-only consistency pass over spec.md, plan.md, tasks.md and the constitution, run before any
code exists, when a gap still costs a sentence instead of a rewrite. Layout and IDs:
~/.mastermind/engineering/core/spec-driven.md. Feature: $ARGUMENTS.
It never edits a file. It reports, then offers fixes the user approves.
Who runs it
The context that wrote the documents already believes they agree. Dispatch a fresh-context subagent with the four files and this skill's six passes, and nothing about how they were written. Where no isolated context exists, run it yourself and label the report self-graded.
The six passes
- Duplication. Two requirements saying the same thing in different words. Keep the clearer one.
- Ambiguity. Adjectives with no number ("fast", "secure", "scalable"), and unfilled template
text:
TODO,???, a template's own<placeholder>lines, unresolved[NEEDS CLARIFICATION]. Angle brackets in command syntax such asnotes add <text>are not placeholders. - Underspecification. A requirement with a verb and no measurable outcome, a story with no acceptance criterion, a task naming a file or component the spec and plan never define.
- Constitution. Any requirement, plan decision or task that conflicts with a
MUST, or a principle the plan's gate markedpassthat the tasks then break. - Coverage. Every
FR-###andUS#/AC#maps to at least one task. Every task maps to a requirement or story, or is setup, foundation or polish. Success criteria needing build work have tasks. - Inconsistency. The same thing named two ways (check the brief's glossary), an entity in the plan absent from the spec, a task ordered before the task it depends on, two requirements that contradict.
Severity
| Level | When |
|---|---|
| CRITICAL | breaks a constitution MUST, a core file is missing, or a P1 requirement has no task |
| HIGH | a duplicate or conflicting requirement, an untestable acceptance criterion, a security or data ambiguity |
| MEDIUM | terminology drift, a non-functional requirement with no task, an underspecified edge case |
| LOW | wording, a minor redundancy |
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.
- 15d ago First seen · 71 lines · 98 tokens per session scan A 152e4fac6bd8
analyze is a skill published in the GitHub repository mehrad-dm/mastermind (23 stars, last pushed 6d ago), licensed MIT. It adds 98 tokens to every session and 972 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
code-review
Run a thorough self-review pass on the most recent change.
code-review
Use when reviewing code for bugs, security issues, performance problems, or adherence to best practices. Provides structured code review with severity levels and actionable feedback.
code-coherence-review
Reviews code and plans for logic coherence, correctness, and structural integrity.
reviewer-architect-adversarial
Adversarial plan review — structural validation and assumption attack on grill artifacts before implementation begins.
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.