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 agentmods add skills/xcrft/mastermind/mastermind-test-auditnpx skills add xcrft/mastermind --skill mastermind-test-auditgit 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-test-audit)<a href="https://agentmods.dev/skills/xcrft/mastermind/mastermind-test-audit"><img src="https://agentmods.dev/badge/skills/xcrft/mastermind/mastermind-test-audit.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.01428 |
| Opus 5 | $0.00034 | $0.00714 |
| Sonnet 5 | $0.00014 | $0.00286 |
| Haiku 4.5 | $0.00007 | $0.00143 |
Grade A, and why
mastermind-test-audit 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 4d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mastermind test audit
A green suite proves that the assertions present passed. It does not prove the change is covered, and it does not prove the assertions were checking the thing that changed. Those are different claims, and only the first one runs automatically.
You are read-only. You report findings and change nothing.
What the controller already established
Do not re-derive these — read them and build on them:
vacuous_test_claiminaudit.mdmeans a verification command provably ran zero tests. The controller checksgo test,pytest,cargo test, and the jest / vitest /npm testfamily, and it stays silent when the answer is undeterminable rather than guessing.missing_testmeans a test the spec planned is absent.signature_changednames symbols whose contract moved.
If audit.md is absent, say so and continue on the diff and the graph. Do not
present the controller's findings as your own, and do not contradict them
without new evidence.
The four checks
1. Changed behaviour no test reaches
mmcg_test_impact --since <baseline> returns candidates per changed symbol with
a classification that is the whole point:
direct— the test is a changed test symbol, or reaches the change at graph depth 1. This is coverage evidence.transitive— reaches it at depth ≥2. Weaker: the test may pass while the changed line never executes.heuristic— a filename matched. This is not coverage. It is a place to look, and treating it as proof is the mistake this check exists to catch.
A changed symbol with no direct candidate is uncovered behaviour. Say which
symbol and what classification you did find; "there are tests nearby" is not an
answer.
2. The test exercises a different path than the change
A suite can be green, on-topic, and still never touch the changed code. Compare
what the test calls with what production calls: mmcg_callees on the test
symbol, mmcg_callers on the changed symbol. When the test calls a wrapper,
a helper, or an older entry point that the real caller no longer uses, the green
result is about a path nobody runs.
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.
- 4d ago First seen · 156 lines · 69 tokens per session scan A 2e238d00b3ec
mastermind-test-audit is a skill published in the GitHub repository xcrft/mastermind (11 stars, last pushed 4d ago), licensed MIT. It adds 69 tokens to every session and 1,428 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
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
orchestrate
Tree-aware multi-agent GitHub-issue pool. Conductor manages task-tree from task-splitting-evaluation, executing depth-first per branch while parallelizing roots/orphans. Each worker agent owns its subtree lifecycle. Conductor tracks state (pending/started/in-progress/completed/halted) in GitHub +…
bonsai-ninja
Use bonsai-ninja as compiler-backed structural evidence when mapping a codebase, finding symbols, tracing behavior, inspecting dataflow, debugging across files, reviewing change impact, exporting graph facts, or running SAST.
task-splitting-evaluation
Recursive pre-implementation GitHub task splitting and evaluation flow. Use when the user wants Claude agents to evaluate unhandled tasks, skip already-processed tasks, mark easy leaves with detailed executor-ready comments, split broad tasks into GitHub subtasks, and keep recursing until every leaf is well described…
gh-task
Run a GitHub issue end-to-end in this repository using the committed isolated-worktree workflow. Use when the user invokes $gh-task, asks to run a GitHub task, or provides a GitHub issue number.
stacklit-navigator
Use stacklit.json to navigate codebases without burning tokens on file exploration.