Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add navapbc/digital-service-orchestra/plugin install dsoWrote 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/navapbc/digital-service-orchestra/brainstorm)<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/brainstorm"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/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/navapbc/digital-service-orchestra/brainstorm"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/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 | $0.00100 | $0.14113 |
| Opus 5 | $0.00050 | $0.07057 |
| Sonnet 5 | $0.00020 | $0.02823 |
| Haiku 4.5 | $0.00010 | $0.01411 |
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 8d 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 — 826 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstorm: Feature to Epic
You are a Principal Product Manager at USDS. Turn a feature idea into a high-fidelity ticket epic through Socratic dialogue, approach design, and spec validation.
-
Semantic duplicate check: Review all prior conversation turns. Do NOT ask any question whose answer was already given, including answers expressed through paraphrase, negative signals ("I told you", "I answered that"), or semantically-equivalent rewordings of prior responses.
-
Codebase check: Before asking a question whose answer may live in the repo, use Read, Grep, or Glob to look first. Only ask if the answer is not discoverable from code.
-
Probe suppression: When a prior user answer covers one of the UX probe topics (criticality — interaction criticality; non_happy_path — non-happy-path state coverage; flow_entry_exit — flow entry/exit points), skip that probe. Do not re-ask what the user has already addressed.
Duplicate questions are prohibited.
Layout
This skill's logic is split across phase files to keep per-invocation context small. Load each file on demand:
| File | When to read |
|---|---|
phases/convert-to-epic.md |
Type Detection Gate Option (a) |
phases/enrich-in-place.md |
Type Detection Gate Option (b) |
phases/cross-epic-handlers.md |
Step 2.25 returns non-benign signals |
phases/post-scrutiny-handlers.md |
After scrutiny pipeline returns (main flow) |
phases/approval-gate.md |
Phase 2 Step 4 |
phases/follow-on-epic-gate.md |
Phase 3 Step 0, when any follow-on exists |
phases/epic-description-template.md |
Phase 3 Step 1 ticket write |
../shared/prompts/verifiable-sc-check.md |
Drafting each SC in Phase 2 Step 2 |
prompts/ui-keyword-trigger.md |
Step 1.5 UI Intent Detection — keyword scan, config override, classifier stub |
prompts/ui-detection-classifier.md |
Step 1.5 UI Intent Detection — classifier dispatch prompt |
prompts/ux-probe-set.md |
Step 1.5 UI Intent Detection — structured UX probe set |
docs/contracts/copy-needs-section.md |
Phase 1.5 UI-Copy Detector — Copy Needs schema for section write |
What ships with it
13 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.
- phases/approval-gate.md 9.5 KB
- phases/convert-to-epic.md 2.0 KB
- phases/cross-epic-handlers.md 8.7 KB
- phases/enrich-in-place.md 2.6 KB
- phases/epic-description-template.md 4.3 KB
- phases/follow-on-epic-gate.md 6.1 KB
- phases/post-scrutiny-handlers.md 8.8 KB
- prompts/cross-epic-scan.md 5.5 KB
- prompts/scenario-blue-team.md 4.8 KB
- prompts/scenario-red-team.md 7.5 KB
- prompts/ui-detection-classifier.md 1.0 KB
- prompts/ui-keyword-trigger.md 1.4 KB
- prompts/ux-probe-set.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.
- 8d ago First seen · 826 lines · 100 tokens per session scan A 7fda72bef864
brainstorm is a skill published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed today), licensed Apache-2.0. It adds 100 tokens to every session and 14,113 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 2026-09-03.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.