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-impactnpx skills add xcrft/mastermind --skill mastermind-test-impactgit 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-impact)<a href="https://agentmods.dev/skills/xcrft/mastermind/mastermind-test-impact"><img src="https://agentmods.dev/badge/skills/xcrft/mastermind/mastermind-test-impact.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 | $0.00060 | $0.00437 |
| Opus 5 | $0.00030 | $0.00218 |
| Sonnet 5 | $0.00012 | $0.00087 |
| Haiku 4.5 | $0.00006 | $0.00044 |
Grade A, and why
mastermind-test-impact 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.
What it actually says
Mastermind Test Impact
Use deterministic candidates to prioritize feedback. Never treat them as proof that omitted tests are unnecessary.
Workflow
-
Choose the same trusted baseline and fresh index used for change analysis. Run
mastermind statusfirst. Stop onindex_staleunless re-indexing is authorized; never infer candidates from a stale graph. -
Run
mastermind impact --since REF --format json, or callmmcg_test_impactfor the exact test projection. -
Reject a response that omits the
focused_tests_do_not_replace_full_gatecaveat. -
Group candidates in this order:
direct: a changed test symbol at depth 0 or a graph-linked test at depth 1;transitive: a graph-linked test at greater depth;heuristic: a filename/component candidate without a proven call path.
-
For each test, retain file, symbol, line, depth, confidence, changed-symbol seeds, and structured evidence. Explain collisions or weak language edges.
-
Run focused tests from high to low confidence for fast feedback, then run every project-required phase/final gate.
Do not invent framework commands. Discover them from repository configuration
and the task spec. Do not call a heuristic candidate “covered”. If graph and
heuristic work were skipped with work_limit, report that no classified
candidates are available. A separately labeled fallback may widen by changed
modules and repository-owned test commands, but it is not direct,
transitive, or heuristic response evidence. Always retain the full gate.
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 · 41 lines · 60 tokens per session scan A 5981b4abf672
mastermind-test-impact is a skill published in the GitHub repository xcrft/mastermind (11 stars, last pushed 4d ago), licensed MIT. It adds 60 tokens to every session and 437 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.