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/superplan-md/superplan-plugin/superplan-brainstormnpx skills add superplan-md/superplan-plugin --skill superplan-brainstormgit clone --depth 1 https://github.com/superplan-md/superplan-pluginWhat 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 | $0.00036 | $0.02039 |
| Opus 5 | $0.00018 | $0.01019 |
| Sonnet 5 | $0.00007 | $0.00408 |
| Haiku 4.5 | $0.00004 | $0.00204 |
Grade A, and why
superplan-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 2d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorming
Overview
Turn real ambiguity into an approved design before planning or execution proceeds.
This skill is for expectation discovery, not decomposition theater.
In Superplan, superplan-brainstorm is a support discipline skill. It does not decide whether Superplan should engage, and it does not own the full shaping phase.
If this skill appears to be the first lane for a repo-work request, stop and hand control back to superplan-entry or the current owning workflow phase.
Hard Gate
Do not invoke implementation skills, shape broad work, or start execution until a design has been presented and approved.
This applies even when the work looks small.
If the right design is only three sentences, write three sentences. Do not skip the design because the work feels obvious.
Anti-Pattern: "This Is Too Simple To Need A Design"
That is rationalization.
Simple work often hides:
- unstated acceptance intent
- taste sensitivity
- hidden constraints
- wrong assumptions about what "done" means
Small work may need a short design. It does not get to skip design discipline.
Trigger
Use when:
- a workflow skill has already established that design clarification is the next blocker
- hidden expectations make direct shaping unsafe
- the user wants something built, changed, or clarified but key constraints are still implicit
- taste, product, or acceptance risk is high enough that the wrong early assumption would increase blast radius
- multiple materially different approaches exist and the trade-off needs approval before planning
- the next blocker is target clarity rather than execution sequencing
Stay Out
Do not use when:
- the request is a simple explanation or answer
- this is first-contact repo work and no workflow skill has routed into design clarification yet
- the work is already clear enough for proportional shaping
- the ambiguity is casual ideation with no durable artifact, visibility, or reusable-context benefit
superplan-entryorsuperplan-routestill needs to decide whether Superplan should engage- the real problem is missing workspace context, which belongs to
superplan-context - the real problem is execution trajectory or artifact depth, which belongs to
superplan-shape
What ships with it
8 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.
- evals/01-stay-out-casual-ideation.md 717 B
- evals/02-brownfield-context-before-questions.md 893 B
- evals/03-overscoped-request-decompose-first.md 782 B
- evals/04-tiny-work-still-needs-short-design.md 905 B
- evals/05-taste-sensitive-approach-approval.md 813 B
- evals/06-substantial-spec-needs-artifact-review.md 873 B
- evals/07-not-first-lane.md 1.0 KB
- evals/README.md 1.7 KB
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.
- 2d ago First seen · 234 lines · 36 tokens per session scan A c3295504337d
superplan-brainstorm is a skill published in the GitHub repository superplan-md/superplan-plugin (72 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 2,039 once invoked, about $0.0002 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
setup
First-run experience for the harness. Three modes: Recommended (guided, 3 min), Full Tour (guided + skill walkthrough, 8 min), and Express (zero questions, 30 sec). Installs hooks first, detects stack, configures harness.json, runs a live demo on real code, and prints a reference card.
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
research
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make…
ascii-diagram
Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.
triage
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to…