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 living-docsgit 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/living-docs)<a href="https://agentmods.dev/skills/mehrad-dm/mastermind/living-docs"><img src="https://agentmods.dev/badge/skills/mehrad-dm/mastermind/living-docs/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/living-docs"><img src="https://agentmods.dev/badge/skills/mehrad-dm/mastermind/living-docs.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 | $0.00116 | $0.01011 |
| Opus 5.5 | $0.00046 | $0.00404 |
| Sonnet 5.5 | $0.00023 | $0.00202 |
| Haiku 4.5 | $0.00012 | $0.00101 |
Grade A, and why
living-docs 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MasterMind: Living docs
Three documents that describe the project as it is today, each fact written once
(~/.mastermind/engineering/core/spec-driven.md). Request: $ARGUMENTS.
| File | Answers | Typical sections |
|---|---|---|
specs/product.md |
who it is for, what problem it solves, what it will never do | users, problem, value, scope and non-goals, key journeys |
specs/business.md |
how it sustains itself and what limits it | model and pricing, market, constraints, compliance, metrics that matter |
specs/tech.md |
how it is built and run | stack, architecture, data, integrations, environments, conventions |
Skeletons: specs/.templates/<file> if present, else templates.md beside this file.
Create a file only when it has content. A library has no business.md.
Write them
- Read before asking. The code, configs, README, CI,
.mastermind/brief.md,specs/, and the existing docs folder. Everything technical is a lookup, never a question. - Ask for what only people know. Who pays, who it is for, what it must never become. One question at a time, each with your recommended answer.
- Mark every unverified line. A claim you inferred and nobody confirmed ends in
(unconfirmed). It loses the mark when the user confirms it or the code proves it. - Point, never copy. A section that would repeat a spec, the constitution or a config file becomes one line linking to it.
- Set the footer. Each file ends with
Last verified: <YYYY-MM-DD> against <commit>. With uncommitted changes, name the last commit plus "working tree".
Keep them true
- After
convergereports converged, promote what the feature taught that outlives it: a new user journey intoproduct.md, a new service intotech.md. Then update the footer date. - When the code contradicts
tech.md, the code wins. Correct the doc in the same change. - Activity is not staleness. Many commits since the footer date are a reason to re-read the doc, never proof it is wrong. Only a fact the code or the user contradicts makes it stale.
- When something contradicts
product.mdorbusiness.md, the document wins until the user says otherwise. Ask them which one is wrong. - Rewrite in place. These describe the present. The history of why lives in
.mastermind/MAP.md(roadmap) and in the frozen feature folders.
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 · 66 lines · 116 tokens per session scan A 7c6c76bff886
living-docs is a skill published in the GitHub repository mehrad-dm/mastermind (23 stars, last pushed 6d ago), licensed MIT. It adds 116 tokens to every session and 1,011 once invoked, about $0.0005 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-execute-blueprint
Use when the user asks to run, execute, implement, or carry out a Strikethroo plan or its blueprint by plan ID in this repository — triggers include execute blueprint, run the plan, implement plan, build the plan. Do not use to create a plan, to only generate tasks, to run a single task, or for generic development…
st-generate-tasks
Use when the user asks to decompose, break down, or generate tasks for an existing Strikethroo plan ID in this repository — triggers include generate tasks, break down the plan, decompose plan, create the task blueprint. Do not use to create a new plan, to execute tasks, or for generic project planning outside…
st-create-plan
Use when the user asks to draft, scope, or write up a new Strikethroo plan for a work order, feature, or initiative in this repository — triggers include create plan, new plan, plan this, scope a plan, strikethroo plan. Do not use to decompose an existing plan into tasks, to execute a plan, or for generic…
plan-management
Plan lifecycle — grill entry point, grounding, artifact review, per-epic execution, revision.
architect-impl-grounding
Grounds the grill's settled decisions in the codebase — annotates impl.md with file paths, signatures, reference files, test specs, and LOC; re-grounds the next epic after each landing.
task-tracking
File-based to-do tracking for multi-step and multi-session work.