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/mehrad-dm/mastermind/lintnpx skills add mehrad-dm/mastermind --skill lintgit clone --depth 1 https://github.com/mehrad-dm/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/mehrad-dm/mastermind/lint)<a href="https://agentmods.dev/skills/mehrad-dm/mastermind/lint"><img src="https://agentmods.dev/badge/skills/mehrad-dm/mastermind/lint.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 5.1 | $0.00090 | $0.01555 |
| Opus 5 | $0.00045 | $0.00777 |
| Sonnet 5 | $0.00018 | $0.00311 |
| Haiku 4.5 | $0.00009 | $0.00155 |
Grade A, and why
lint 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 5d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MasterMind: Lint
Instruction text rots in a specific way: rules accumulate, the same principle gets restated in three layers, and prohibitions pile up long after the model outgrew needing them. Anthropic removed ~80% of Claude Code's system prompt with no measured loss, and named the mechanism of harm: accumulated guardrails produce conflicting instructions, so the model spends its reasoning reconciling them before it can act. This skill finds that drift in MasterMind itself.
It reports. It never edits. Every finding comes back as a proposal you approve or reject, see the guard at the bottom for why that constraint is not negotiable.
Pass A: deterministic, near-free
Run the script; don't do this by hand:
node scripts/lint-brain.mjs # add --strict to exit non-zero on high findings
Run it from the MasterMind clone. An installed brain ships only build-router.mjs and
check-integrity.mjs, not this one: if that's where you are, say so and run Pass B alone rather
than hand-counting.
Counting is not judgment, so it shouldn't depend on a model remembering to do it: and a hand-count drifts between runs, which makes two reports incomparable. The script reports every item below, sorted by severity, with the always-loaded vs on-demand token budget at the top:
- Negative-framing density:
never,don't,do not,avoid,must notper file. Flag files well above the corpus median. (A negative measurably loads the concept it forbids, so each one should be paying for itself.) - Cross-layer repetition: the same normalized sentence in kernel ↔ core ↔ skill ↔ agent. Two layers is a smell, three is where contradictions come from.
- Near-duplicates within a file: the same rule said twice in different words.
- Size and budget: lines and characters per file, split by always-loaded vs on-demand, with a token estimate. The always-loaded number is the one that matters.
- Stale references:
~/.mastermind/…paths, and skill/agent names, that no longer exist on disk.
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.
- 5d ago First seen · 114 lines · 0 tokens per session scan A c4c1e712a7ef
lint is a skill published in the GitHub repository mehrad-dm/mastermind (24 stars, last pushed 6d ago), licensed MIT. It adds 90 tokens to every session and 1,555 once invoked, about $0.0005 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
triage
Triage GitHub issues by applying type, effort, priority, and area labels. Runs in an isolated context to avoid polluting the main conversation with issue details. Delegates to a specialized triage agent with label validation hooks.
docker-extend
Use when: User wants to extend Docker with custom tools, personalize the Docker environment, or set up user-specific Docker customization. Triggers: 'extend docker', 'docker-extend', 'add tools to docker', 'customize docker', 'add my tools to the container', 'personalize docker setup', 'docker user setup', 'install…
writing-git-commits
Write clear, focused Git commit messages and keep commits easy to review.
st-full-workflow
Use when the user asks to run the complete end-to-end Strikethroo workflow for a work order in one shot in this repository — triggers include full workflow, end-to-end, plan and execute, do everything, run the whole strikethroo workflow. Do not use when the user wants only one stage (create a plan, generate tasks, or…
st-refine-plan
Use when the user asks to review, refine, improve, interrogate, pressure-test, or update an existing Strikethroo plan by plan ID in this repository — triggers include refine plan, improve plan, review plan, red-team the plan, update plan. Do not use to create a new plan, to generate tasks, or for generic brainstorming…
hatch3r-board-refresh
Regenerates the living board overview dashboard from current board state. Scans all open issues, computes health metrics, and updates the meta:board-overview issue.