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 commands/yourtechbud/coding-harness-config/setup-brainstorming-artifactsgit clone --depth 1 https://github.com/YourTechBud/coding-harness-configWhat 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 | $0.00014 | $0.01054 |
| Opus 5 | $0.00007 | $0.00527 |
| Sonnet 5 | $0.00003 | $0.00211 |
| Haiku 4.5 | $0.00001 | $0.00105 |
Grade A, and why
setup-brainstorming-artifacts 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up or revise a brainstorming artifact workspace for this repo.
Do not treat this as a setup wizard. Treat it as a guided discovery process that helps the user figure out what kind of artifact workspace would meaningfully reduce cognitive load for their brainstorming process.
<operating_model>
- Start with lightweight, read-only repo discovery: check whether
.isagi/brainstorming-workspaceexists, inspect any existing guidance, and understand repo tooling only enough to avoid bad setup assumptions. - Use repo context as background, not as the main frame of the first conversation.
- Move through the work in gated stages. Internally, use stages to avoid collapsing discovery, onboarding, option discussion, and implementation into one turn. Externally, use natural language unless labels help clarity.
- After read-only discovery, do not move to a new stage without explicit user consent.
- Do not create or modify files until the user has explicitly confirmed the desired artifact experience, the principles to encode, the setup direction, and permission to implement.
- If the user asks to skip questions and "just set it up," keep the discovery lightweight, but still establish the minimum shared understanding needed before implementation. </operating_model>
<seed_principles> Use these as internal lenses during discovery and guidance creation. Do not present them as a mandatory checklist, and do not preserve rejected principles in the final workspace guidance.
- Reduce cognitive burden; the workspace should make long brainstorming easier to stay inside.
- Chat conducts; artifacts carry substantial reasoning.
- Questions should live with relevant branch context, not as detached chat lists.
- Active decision branches should usually be the main unit.
- Branches need predictable high-level anatomy, but their bodies should stay freeform; do not hardcode a universal branch body template.
- Real pushback should be visible when present.
- Artifacts should develop suggestions, tradeoffs, and options, not only questions.
- Visual form should compress thought, not decorate it.
- Minimal, quiet UI usually beats design-heavy presentation.
- Prefer linear, predictable reading flows over bento grids or dashboard-like layouts.
- Navigation should make the workspace easy to re-enter.
- Anti-staleness should not become amnesia; preserve important cumulative context.
- Implementation plans should be created only when explicitly requested. </seed_principles>
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 · 70 lines · 14 tokens per session scan A 26c257dd3386
setup-brainstorming-artifacts is a command published in the GitHub repository YourTechBud/coding-harness-config (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,054 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.