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 YSAA1/harness-workflow --skill brainstormgit clone --depth 1 https://github.com/YSAA1/harness-workflowWrote 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/ysaa1/harness-workflow/brainstorm)<a href="https://agentmods.dev/skills/ysaa1/harness-workflow/brainstorm"><img src="https://agentmods.dev/badge/skills/ysaa1/harness-workflow/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/ysaa1/harness-workflow/brainstorm"><img src="https://agentmods.dev/badge/skills/ysaa1/harness-workflow/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 | $0.00119 | $0.03286 |
| Opus 5.5 | $0.00048 | $0.01314 |
| Sonnet 5.5 | $0.00024 | $0.00657 |
| Haiku 4.5 | $0.00012 | $0.00329 |
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 15d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Approach Brainstorming (Frontier Grill)
The subject of the brainstorm is the approach: open the approach space in conversation, settle it round by round, then write the Spec that records the outcome → plan. No production code, no Executable Plan.
Leading words: frontier · design tree · shared understanding
Canonical Spec: docs/specs/YYYY-MM-DD--<topic>.md (override only when the user or AGENTS.md explicitly names a path). By default, do not write .harness/; the sole exception: when the project already has a .harness/ recovery surface, perform "register on write" (see Flow steps 1–2).
User-visible language follows the user; protocol tokens (BRAINSTORM …, Spec, Gate, paths) may stay in English.
Routing
- Use: open-ended intent, unsettled approach, grilling wanted. Vagueness is not a reason to wait — it is the thing this session eats.
- Don't: Spec already approved; single-point small patch; only a factual answer wanted.
- Next: Spec approved →
plan; workbench gap → (after Spec approval or when the user explicitly says so)harness-builder.
Gears
The depth dial belongs to the user; the agent never sets it silently:
- Invocation:
brainstorm <topic>may carry a gear (low/medium/high; natural language works too: "low gear / fewer questions", "high gear / dig deeper / research-grade / I'm stuck on a bottleneck"). Unspecified means medium; the first round's banner states the gear; the user retunes with one word at any time, and the gear follows the user's exact words. - Inference (must be stated, and vetoable): infer low only when the user's own words anchor goal + boundaries and it is clearly a small matter; infer high only when the user explicitly says bottleneck/innovation/research; everything else is medium.
- Gears change only the question-surface width and grilling intensity; rounds always follow the frontier — no round quotas (no minimum round count, settled decisions are not re-asked).
What ships with it
5 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.
- 15d ago Changed a417f6969c4e
- 25d ago Changed · +29 lines · +29 tokens per session e9da7defa0d6
- 29d ago Changed · +12 lines 21f543cdea64
- 1mo ago Changed · +19 lines · +25 tokens per session 4bcf0b5fd916
- 1mo ago Changed · +44 lines · +22 tokens per session b20c3cbc5055
- 1mo ago Changed · -43 lines · -22 tokens per session ebad4a7d24d3
- 1mo ago First seen · 73 lines · 65 tokens per session scan A c3aad0b82345
brainstorm is a skill published in the GitHub repository YSAA1/harness-workflow (3 stars, last pushed 16d ago), licensed MIT. It adds 119 tokens to every session and 3,286 once invoked, about $0.0005 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
better-harness
Use when /better-harness reviews the outer coding-agent Harness for lifecycle controls, repeated work, project feedback, agent assets, session outcomes, repair planning, durable reports, finding-bound fixes, or manual direct fixes. Invoke only via slash command.
diagnose-backend-bug
Diagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do…
reproduce-frontend-bug
Build a bounded, replayable browser or UI bug reproduction from GitHub Issues, Jira, Aone, user-provided exports, screenshots, videos, comments, or attachments. Use for browser, WebView, IDE or desktop UI, interaction, responsive, rendering, accessibility, or visual defects that need evidence-preserving reproduction…
intent-correlation-analysis
Analyze a bounded IntentCorrelationPacketV1 and propose reviewable links among user inputs, execution slices, change units, commits, artifacts, and validation outcomes. Use when reconstructing why an observed coding-agent change exists or when Studio needs evidence-backed Intent correlation. Do not use for raw…
generate-harness-dsl
Generate, revise, or review complete Harness as Code .harness files when a coding-agent workflow, agent role, skill, tool contract, MCP connection, runtime, or deployment must be compiler-valid and resolvable with @qoder-ai/harness.
memory-recap
Create evidence-linked work profiles, diagnose Coding Agent collaboration friction, and recommend concrete improvements from native memories or frozen exports. Use for memory recaps and agent-usage retrospectives, not memory maintenance or session-performance measurement.