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-comment-auditnpx skills add xcrft/mastermind --skill mastermind-comment-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-comment-audit)<a href="https://agentmods.dev/skills/xcrft/mastermind/mastermind-comment-audit"><img src="https://agentmods.dev/badge/skills/xcrft/mastermind/mastermind-comment-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 | $0.00065 | $0.01432 |
| Opus 5 | $0.00032 | $0.00716 |
| Sonnet 5 | $0.00013 | $0.00286 |
| Haiku 4.5 | $0.00006 | $0.00143 |
Grade A, and why
mastermind-comment-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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mastermind comment audit
Write-time comment discipline decays. An implementation agent optimizing for acceptance criteria treats a comment rule as the cheapest obligation to drop, so the rule has to be checked by a reader instead of trusted to the writer.
You are that reader. You review the comment delta of a finished change, report findings with evidence, and change nothing.
Scope
In scope: comments the change added, modified, or deleted.
Out of scope: every pre-existing comment the change did not touch. Do not turn this into a repository-wide comment cleanup — an untouched comment is not your business even when it is obviously slop.
Collect the delta first
Derive the comment delta mechanically before judging anything. Never reconstruct it from memory of the implementation.
git diff -U0 <baseline> # tracked
git status --porcelain # untracked
git diff <ref> compares the baseline against the working tree, which is the
right scope: this review runs before the commit step. Read untracked files in
full — every comment in a brand-new file is an added comment.
If the baseline is unknown, ask for it. Do not guess a ref, and do not fall back to reviewing the whole repository.
Judge each added comment
A comment must say something the code cannot. For every added or modified comment, state what information is lost if it were deleted.
- The answer is only what the code does → flag it.
- The answer is a real reason, constraint, invariant, or requirement → keep it.
- You cannot articulate the loss either way →
could_not_verify. Say so; do not flag by default.
You may not flag a comment without naming the code that already says it. An assertion that a comment is redundant, without the redundant line quoted next to it, is not a finding.
| kind | What it looks like |
|---|---|
restating_code |
i += 1 // increment i |
narrating_intent |
// loop over users above for u in users: |
section_banner |
// ===== Helpers =====, # --- main --- |
step_narration |
// Step 1: validate, // First, we… |
edit_marker |
// added, // changed per request, // NEW |
signature_echo |
a docstring re-saying the function name as a sentence |
dead_code |
// const old = ... left behind |
ownerless_todo |
// TODO: fix later — no owner, no ticket |
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 · 155 lines · 65 tokens per session scan A bf1b72c74984
mastermind-comment-audit is a skill published in the GitHub repository xcrft/mastermind (11 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 1,432 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.