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 OutlineDriven/outline-driven-development --skill brainstormgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/brainstorm)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/brainstorm"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/brainstorm.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 27 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00044 | $0.03547 |
| Opus 5 | $0.00022 | $0.01774 |
| Sonnet 5 | $0.00009 | $0.00709 |
| Haiku 4.5 | $0.00004 | $0.00355 |
Grade A, and why
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 yesterday.
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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge brainstorm
Contract
| Field | Bound contract |
|---|---|
| Trigger | User begins nontrivial knowledge work with notes, a transcript, a brain dump, or a problem to think through (mode: dump); asks to brainstorm, asks what to build, or wants divergent ideas on a subject (mode: ideate); or faces a question genuinely clearer shown than told and approves a local browser view (mode: visual). |
| Authority | Reversible local: writes only plans/brainstorm-{descriptive-name}.md, docs/ideation/<slug>.md plus <slug>.html when format:html is given, .odin/brainstorm/session-<24-hex> session data, and OS-temp visual probe files; rollback is deleting those files and stopping the named managed process. No remote mutation. |
| Side effect | Reads prior knowledge in docs/knowledge/, plans/, and docs/solutions/; mode visual starts a local key-gated HTTP and WebSocket server with an idle timeout and retains its session directory. No other file, VCS, credential, paid, published, or remote change. |
| Done | The active mode's done state holds: dump — the user's language is structurally captured, prior context or its honest absence is shown, tensions and gaps are identified, at most three load-bearing questions are resolved, a reasoned direction is offered, and the origin file is written before plan; ideate — the ideation document records grounded survivors and a reason for every rejection, each candidate cites its basis, one reviewer adjudicated the complete pool, and the result ends at intent clarification; visual — the user saw the options, validated browser events merged with the terminal reply, and the server is stopped or left to its idle timeout. |
Inputs
mode:dump(default),ideate, orvisual. Select from the request; when ambiguous, ask once.- Mode
dump: the brain dump — pasted meeting notes or transcript, voice-to-text output, bullet points, a document link or path, or loose narration. Optional at invocation; if absent, prompt for it before proceeding and stop if none arrives. Optional, mid-flow: the user's answers to the load-bearing questions.docs/knowledge/,plans/, anddocs/solutions/need not exist; absence is an honest result, not an error. - Mode
ideate: an identifiable divergent subject (required), an optional leadingformat:htmlflag, and the operating repository as the grounding corpus. If the root containsSTRATEGY.md, use it as optional strategic context; its absence is not an error. Derive<slug>by lowercasing the subject, replacing each run of non-alphanumeric characters with one hyphen, and trimming leading and trailing hyphens; reject an empty result. - Mode
visual: a visual question — a real mockup, layout, diagram, visual comparison, or spatial relationship — plus the project directory. Optional: idle timeout in minutes from 1 through 1440 (default 240). Requires Bun exactly1.4.0and a host managed-process primitive that launches, reads readiness and exit, and stops a long-running process by one stable name; without either, fail explicitly.
What ships with it
15 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.
- agents/openai.yaml 245 B
- references/agents-repo-profiler.md 2.8 KB
- references/agents-slack-researcher.md 8.3 KB
- references/brainstorm-sections.md 10.0 KB
- references/handoff.md 7.7 KB
- references/html-rendering.md 17 KB
- references/markdown-rendering.md 9.8 KB
- references/repo-profile-cache.md 4.0 KB
- references/synthesis-summary.md 9.0 KB
- references/universal-brainstorming.md 4.5 KB
- references/visual-companion.md 24 KB
- references/visual-probes.md 6.8 KB
- scripts/repo-profile-cache.py 13 KB runs code
- scripts/visual-companion-server.ts 17 KB runs code
- scripts/visual-probe-server.js 12 KB runs code
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.
- yesterday Changed · +20 lines · -14 tokens per session 036b0ccce40e
- 4d ago First seen · 55 lines · 58 tokens per session scan A 985ab1a438c4
brainstorm is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 44 tokens to every session and 3,547 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 2026-09-03.
Other skills, from other repositories
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
duet
Use when the user invokes /duet, says "pair with me", or faces aesthetic, architectural, or irreversible decisions.
goal-prompt-drafting
Use when asked to draft copy-ready /goal objectives for long-running agents; returns one normalized one-line objective with measurable end state, grounded proof, easy-out invariants, a stop clause, and a Missing list. Not for source or remote-system changes.
handoff-prompt
Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.
publish-branch
Use when asked to publish the checked-out branch: commit and push it on whatever branch it is, the default branch included. Not for creating branches, PRs, force pushes, or pushing any other branch; when the request excludes the default branch, use commit-push-current.
drill
Use when a concept needs practising rather than explaining: run a scaffolded exercise from worked example to independent problem, quiz the learner, run spaced recall over what they cleared, or probe for the gaps blocking what they want next. For explanation, use explain-concept; for an end-to-end build, use capstone.