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 xcrft/mastermind --skill mastermind-product-intakegit clone --depth 1 https://github.com/xcrft/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/xcrft/mastermind/mastermind-product-intake)<a href="https://agentmods.dev/skills/xcrft/mastermind/mastermind-product-intake"><img src="https://agentmods.dev/badge/skills/xcrft/mastermind/mastermind-product-intake.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00066 | $0.01177 |
| Opus 5 | $0.00033 | $0.00589 |
| Sonnet 5 | $0.00013 | $0.00235 |
| Haiku 4.5 | $0.00007 | $0.00118 |
Grade A, and why
mastermind-product-intake 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 8d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mastermind product intake
A PRD is written to decide whether to build something. A task contract is written to check whether it was built. They are different documents, and pasting the first into the second produces acceptance criteria that no gate can fail.
This is a planning step. It converts; it does not implement, and it does not judge whether the work is worth doing.
Name the source
Record the PRD, ticket, or document with a stable reference — an ID or a URL, not a title. "Per the spec" is unauditable: a product doc that moved on cannot be told apart from an implementation that drifted.
Sort every statement into three piles
This is the whole job, and most of the value is in refusing to blur them.
Behaviour — what the system does, observable at merge time. "An archived invoice is excluded from the export." This becomes acceptance criteria.
Constraint — a bound the behaviour must respect. "The export completes within 30 seconds for 10,000 invoices." This becomes a criterion only if you also name how it is measured. Unmeasured, it is decoration that reads like rigour.
Outcome — why the work exists. "Reduce support tickets about missing invoices." This is never acceptance criteria. It cannot fail at merge time, it resolves weeks later in production if anyone looks, and putting it in the contract means a mechanical gate marks it satisfied while nobody has measured anything.
A criterion that cannot fail on the day the change lands belongs in the outcome section, no matter how central it is to the PRD.
Resolve the nouns
Product writing names things: invoice, export, workspace, role, plan. Search each one before assuming it is new.
mmcg_search Invoice
mmcg_search exportInvoices
mmcg_api_surface src/billing/
A feature that reads as new is usually mostly existing surface with a gap in the middle. Say which nouns already exist as symbols, which exist under a different name, and which are genuinely new — that distinction changes the scope, the risk, and often the mode.
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.
- 8d ago First seen · 136 lines · 66 tokens per session scan A 168756bff22b
mastermind-product-intake is a skill published in the GitHub repository xcrft/mastermind (11 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 1,177 once invoked, about $0.0003 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
projectatlas
Use ProjectAtlas as the atlas-first orientation layer before broad source reads, with MCP-first task startup, short-alias worktree registration and routing, safe targeted initialization, ranked navigation, exact or federated graph evidence, purpose curation, health, lint, and repository-wide token reporting.
truecourse-hooks
Install, configure, or remove the TrueCourse pre-commit hook.
codex-coding-plugin
Build, review, or fix ProjectAtlas plugin/runtime installer integration for Codex, Claude Code, and OpenCode, especially version convergence, stale ProjectAtlas cache repair, MCP config generation, skill artifacts, host smoke tests, and fake-host tests for ProjectAtlas releases.
cymbal
Tree-sitter indexed code navigator. Use the cymbal CLI — not Read, Grep, Glob, or Bash — for finding where symbols are defined, tracing callers and callees, locating interface implementations, understanding the impact of a change, and mapping imports across an existing codebase. Returns precise, token-efficient…
repo-harness
Route explicit repo-harness setup, planning, execution, verification, and handoff actions through deterministic repository state.
obsidian-memory
Cross-project long-term memory over an Obsidian brain vault: recall relevant notes before a task, and persist distilled conclusions (decisions, pitfalls, solutions, progress) back after a task. The vault is an optional aggregation/projection layer — repo-local artifacts stay the per-project source of truth, and sync…