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 maxence2997/mx-harness --skill mx-brainstormgit clone --depth 1 https://github.com/maxence2997/mx-harnessWrote 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/maxence2997/mx-harness/mx-brainstorm)<a href="https://agentmods.dev/skills/maxence2997/mx-harness/mx-brainstorm"><img src="https://agentmods.dev/badge/skills/maxence2997/mx-harness/mx-brainstorm/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/maxence2997/mx-harness/mx-brainstorm"><img src="https://agentmods.dev/badge/skills/maxence2997/mx-harness/mx-brainstorm.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00076 | $0.01998 |
| Opus 5.5 | $0.00030 | $0.00799 |
| Sonnet 5.5 | $0.00015 | $0.00400 |
| Haiku 4.5 | $0.00008 | $0.00200 |
Grade A, and why
mx-brainstorm 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 25d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mx-brainstorm
Trigger
/mx-brainstorm <topic>
/mx-brainstorm
Operating principles
Don't assume. Don't hide confusion. Surface tradeoffs. These apply at every step below — not just Step 1.
- State assumptions explicitly. If uncertain, ask rather than guess — in design, a question costs less than a wrong assumption. Mark each question [design] when its answer can change the approach, or [detail] when the approach holds either way.
- Present multiple interpretations. When the user's request is ambiguous, surface the readings and let the user pick. Do not silently choose one and proceed.
- Push back when warranted. If a simpler approach exists, say so. If a proposed option is over-engineered for the stated problem, name it.
- Stop when confused. Name what is unclear and ask for clarification. Do not paper over confusion with plausible-sounding text.
Applied to this skill specifically:
- In Step 2, options must be genuinely distinct — do not pad to three options by inventing a contrived variant. Two real options beats three fake ones.
- In Step 2, prefer the minimum approach that solves the stated
problem. Larger options must justify their extra scope explicitly in
Best when.
Side requests
At any step, the user may ask for something mid-conversation (e.g. "open an issue", "add a comment", "check a file"). When this happens:
- Execute exactly what was requested — nothing more
- Do not make additional code changes, file edits, or actions that were not asked for
- After completing the side request, return to the brainstorm conversation
Example: "go open an issue describing this" → open the issue, stop. Do not also edit source files.
Step 1 — Understand the idea
Exit early if the change is small enough that the spec would restate the diff: a single obvious fix, one call site, no design choice to make. Say "this is small enough to skip the spec — I'll do it directly" and stop. If the user disagrees, continue. Not under an orchestrator: when mx-flow invoked this skill the user already chose the full flow — write the spec.
What ships with it
2 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.
- 25d ago Changed · +7 lines cd4a54a899eb
- 1mo ago Changed · +37 lines · +2 tokens per session 29a82fbbf2f6
- 1mo ago First seen · 181 lines · 74 tokens per session scan A 68f5cc0f9b0f
mx-brainstorm is a skill published in the GitHub repository maxence2997/mx-harness (5 stars, last pushed 25d ago), licensed MIT. It adds 76 tokens to every session and 1,998 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
code-refiner
Deep code simplification and refactoring preserving behavior across Python, Go, TypeScript, Rust. Targets complexity, anti-patterns, readability debt. Triggers on: "simplify this code", "refactor for clarity", "reduce complexity", "make this more readable", "tech debt cleanup", "too much nesting".
package-evaluator
Use when evaluating an Armory package, auditing agent or hook quality, checking package completion contracts, or reviewing the catalog across package types. Covers single-package and repository-wide audits. Not for LLM prompt optimization or ordinary PR code review.
codebase-advisor
Senior codebase advisor that audits a repository, vets findings, and writes self-contained implementation plans for other agents to execute. Triggers on: "write improvement plans", "create an implementation backlog", "audit and plan fixes", "turn findings into plans", "agent-executable plans", "reconcile plans"…
pr-review
Diff-based PR review across code quality, test coverage, silent failures, type design, and comment quality with severity-ranked findings. Triggers on: "review my PR", "review this code", "check my changes", "audit this PR", "code review". NOT for pre-landing gate, use pre-landing-review.
devils-advocate
Challenges AI-generated plans, code, and designs via pre-mortem, inversion, and Socratic questioning to surface blind spots and failure modes. Triggers on: "challenge this", "devils advocate", "stress test this plan", "poke holes in this", "what am I missing".
package-optimizer
Evaluate one existing package or bounded package family from recorded evaluator evidence and a capability profile, then propose retain, simplify, strengthen, retire, or inconclusive without editing. Use when optimizing a skill, agent, hook, rule, command, utility, or preset; evaluating whether package detail is…