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 jscraik/Agent-Skills --skill he-brainstormgit clone --depth 1 https://github.com/jscraik/Agent-SkillsWrote 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/jscraik/agent-skills/he-brainstorm)<a href="https://agentmods.dev/skills/jscraik/agent-skills/he-brainstorm"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/he-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/jscraik/agent-skills/he-brainstorm"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/he-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 | $0.00059 | $0.02135 |
| Opus 5.5 | $0.00024 | $0.00854 |
| Sonnet 5.5 | $0.00012 | $0.00427 |
| Haiku 4.5 | $0.00006 | $0.00214 |
Grade A, and why
he-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 1mo 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Engineering Brainstorm
Philosophy
Make ambiguity useful without ceremony. Preserve stated facts, inferred bets,
guesses, and out-of-scope work so the next HE stage can continue without
re-litigating context. Local AGENTS.md, rules, hooks, command boundaries, and
approval gates outrank this skill.
When to Use
Use when intent, terminology, expected behavior, tradeoffs, scope, idea quality,
or next HE stage is unsettled before spec, plan, Linear, review, or
implementation. Use folded he-ideate mode when the user asks what to improve,
asks for options, wants ornate ideas filtered, wants dropped leverage recovered,
or wants strong ideas before selecting one to brainstorm.
Use domain_interview mode when the user asks to be interviewed through a
design tree, resolve ubiquitous language, challenge project terms, or update
UBIQUITOUS.md before downstream specification or planning.
When Not to Use
Do not use for selected execution slices, direct implementation, concrete bug fixes, approved specs, or approved plans. Route to the matching HE stage or implementation skill.
Inputs
User goal, identifiable subject, repo/Linear/session/.harness evidence,
constraints, rejected ideas, and success criteria.
Outputs
Return schema_version when structured; stated facts; inferred bets; guesses;
out-of-scope work; options/survivors; risks; warrants; scope_tier;
blackboard_delta; validation or blocker status; artifact path when written;
and next HE stage. Brainstorm artifacts live under .harness/brainstorm/**.md;
folded he-ideate artifacts live under .harness/ideate/**.md.
Preconditions
Identify a subject before candidate generation. Inspect cited repo, Linear,
session, or .harness evidence before treating it as fact. Classify side
effects before acting: read-only, .harness artifact write, external write,
repo write, or destructive.
Procedure
- Explore first and require an identifiable subject before dispatching ideation or writing artifacts.
- If cited evidence cannot be read, still return the brainstorming frame with
validation: blocked,blocked_reason, explicitly labeled assumptions, and the smallest safe recovery step; do not replace the output with a generic request for pasted content. - Resolve only the stage context fields needed for tracker, artifact route, evidence freshness, and coding-harness handoff.
- Separate stated facts, interpretations, guesses, and out-of-scope work.
- Keep scope tight: start with 2-3 focused surfaces and widen only when the ambiguity cannot be resolved from the initial evidence.
- Route durable brainstorm artifacts to
.harness/brainstorm/**.md; route explicit foldedhe-ideateartifacts to.harness/ideate/**.md. - Resolve or block the Linear tracker before durable handoff for tracked work.
- In folded
he-ideatemode, usereferences/ideation-mode.mdfor candidate generation, critique, coverage recovery, survivor selection, web research, and specialist-skill steering. - Apply the first-principles contract before survivor selection: prefer ideas that prevent verified HE failures or reduce ambiguity; defer copied patterns that lack HE-specific failure evidence.
- Apply the BLUF review contract to non-trivial durable brainstorm or ideation artifacts so the selected survivor, uncertainty, risk consequence, and next HE stage are visible before option detail.
- Ask before survivor selection when the chosen survivor would shape downstream spec, plan, Linear work, or implementation scope.
- In
domain_interviewmode, apply the ubiquitous-language contract: inspect repo language and code evidence before asking, userequest_user_inputfor one bounded branch question at a time when available, updateUBIQUITOUS.mdor the selected context-specific ubiquitous file inline when a glossary term is resolved, and never store implementation decisions in the ubiquitous language file.
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.
- agents/openai.yaml 216 B
- assets/icon-large.png 47 KB
- assets/icon-small.png 2.5 KB
- references/brainstorm-workflow-details.md 2.0 KB
- references/contract.yaml 6.4 KB
- references/discovery-interview.md 1.8 KB
- references/document-review-pass.md 672 B
- references/evals.yaml 11 KB
- references/hot-path-folded-context.md 4.8 KB
- references/ideation-mode.md 5.0 KB
- references/requirements-artifact-guide.md 1.0 KB
- references/task-profile.json 1.3 KB
- references/visual-communication.md 633 B
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.
- 1mo ago Changed · +62 lines · +18 tokens per session 1119aa348b0e
- 1mo ago First seen · 144 lines · 41 tokens per session scan A 6da687f39856
he-brainstorm is a skill published in the GitHub repository jscraik/Agent-Skills (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 59 tokens to every session and 2,135 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
worker-integration
Worker-Agent integration for intelligent task dispatch and performance tracking.
agui-dotnet-streaming-chat
Get started with the AG-UI .NET SDK: bootstrap and run your first streaming-chat app (client + server) with the AG-UI .NET NuGet packages (AGUI.Client, AGUI.Server, AGUI.Formatting, AGUI.Abstractions). USE FOR: which packages to install and how to wire them; constructing an AGUIChatClient against an endpoint and…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…