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-architecture-reviewgit 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-architecture-review)<a href="https://agentmods.dev/skills/xcrft/mastermind/mastermind-architecture-review"><img src="https://agentmods.dev/badge/skills/xcrft/mastermind/mastermind-architecture-review/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/xcrft/mastermind/mastermind-architecture-review"><img src="https://agentmods.dev/badge/skills/xcrft/mastermind/mastermind-architecture-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00076 | $0.01217 |
| Opus 5 | $0.00038 | $0.00609 |
| Sonnet 5 | $0.00015 | $0.00243 |
| Haiku 4.5 | $0.00008 | $0.00122 |
Grade A, and why
mastermind-architecture-review 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 9d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mastermind Architecture Review
Review whether a design preserves the system's runtime invariants. Do not turn the review into a generic architecture checklist or redesign the system merely because another style is possible.
Boundaries
- [[mastermind-project-map]] supplies bounded structural navigation; it does not prove a request, event, or write reaches production code at runtime.
- [[mastermind-change-impact]] supplies syntactic blast-radius evidence; it does not prove semantic compatibility.
- [[mastermind-critical-review]] is the general proposal rubric. Use this skill when the decision specifically crosses runtime, state, retry, or evolution boundaries.
This is a read-only review. It may require a design change, but it does not implement one.
Inputs
- Decision — the architecture or change being reviewed.
- Scope — affected components, interfaces, state, and deployment boundary.
- Evidence — codegraph results, entry points, handlers, schemas, storage code, tests, configs, deployment facts, or an explicit evidence gap.
- Baseline — current contract or behavior when compatibility is relevant.
Never replace missing evidence with a familiar architecture pattern.
Review workflow
-
State the decision and the system invariant it must preserve.
-
Gather the narrowest evidence that can prove the actual path: indexed structure first, then read the entry point, boundary adapter, domain logic, state owner, and externally visible contract. Treat dynamic dispatch, framework registration, queues, reflection, and infrastructure routing as runtime evidence gaps until verified directly.
-
Reconstruct the path as ordered hops:
trigger -> transport -> admission/auth -> domain operation -> state owner -> external side effect -> response/eventOmit hops that do not exist; never add conventional layers by assumption.
-
Load only the references implicated by the design:
- process, service, queue, trust, or serialization crossings:
references/runtime-boundaries.md - authoritative and derived state, caches, indexes, replicas, or dual writes:
references/source-of-truth.md - retries, webhooks, commands, jobs, payments, or at-least-once delivery:
references/idempotency.md - API, event, schema, config, CLI, persisted-data, or rolling-deploy changes:
references/backward-compatibility.md
- process, service, queue, trust, or serialization crossings:
-
For each material risk, describe one concrete failure sequence. Name the invariant at risk, the evidence, and the boundary where it can fail.
-
Bind every required change to a verification method that would fail before the change: a contract test, integration test, concurrent retry test, replay test, migration rehearsal, or production observation.
-
Give a bounded verdict. Unknown runtime facts stay unknown.
What ships with it
5 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.
- 9d ago First seen · 130 lines · 76 tokens per session scan A ffb9fee22c58
mastermind-architecture-review is a skill published in the GitHub repository xcrft/mastermind (11 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 1,217 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
sem
Use sem to get entity-level (function/class/method) semantic diffs, impact analysis, blame, and dependency context from any Git repo. Trigger this skill whenever the user asks what changed in a commit or PR, wants to understand the blast radius of a change, needs to know who last modified a function, wants to trace…
sem
Semantic version control CLI. Entity-level diffs for Git (functions, classes, methods instead of lines).
truecourse-analyze
Run TrueCourse architecture analysis on this repository.
lsp-inspect
Full code quality audit for a file, package, or directory. Supports batch mode (directory walk with --top ranking), comparison mode (--diff for branch-only issues), severity calibration by blast radius, fix suggestions, and confidence tiers. Applies a check taxonomy (dead symbols, silent failures, error wrapping…
trace-mcp-refactoring
Safe refactoring workflow using trace-mcp — assess risk, find candidates, check impact, and rename symbols across all files without missing import sites or cross-file references.
lsp-dead-code
Enumerate exported symbols in a file and surface those with zero references across the workspace. Use when auditing for dead code, cleaning up APIs, or checking which exports are safe to remove.