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/ddunnock/claude-plugins/concept.spitballgit clone --depth 1 https://github.com/ddunnock/claude-pluginsWrote 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/commands/ddunnock/claude-plugins/concept.spitball)<a href="https://agentmods.dev/commands/ddunnock/claude-plugins/concept.spitball"><img src="https://agentmods.dev/badge/commands/ddunnock/claude-plugins/concept.spitball.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.01149 |
| Opus 5 | $0.00013 | $0.00575 |
| Sonnet 5 | $0.00005 | $0.00230 |
| Haiku 4.5 | $0.00003 | $0.00115 |
Grade A, and why
concept:spitball 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 4d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/concept:spitball
Phase 1 of concept development: open-ended ideation.
Prerequisites
- Session initialized (
/concept:init). Verify state.json exists:
If this fails, tell the user to runpython3 ${CLAUDE_PLUGIN_ROOT}/scripts/update_state.py --state .concept-dev/state.json show/concept:initfirst and stop.
Procedure
Step 1: Set Phase
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/update_state.py --state .concept-dev/state.json set-phase spitball
Step 2: Open the Floor
Present an open invitation — no structure, no forms:
===================================================================
SPIT-BALL SESSION
===================================================================
This is the wild ideas phase. There are no bad ideas here.
Tell me what you're thinking about. It can be:
- A problem you've noticed
- A capability you wish existed
- A "what if..." scenario
- Something that annoys you about how things work today
- A half-formed thought you haven't fully explored
I'll ask follow-up questions, probe feasibility where useful,
and help you explore the idea space. We'll cluster themes later.
What's on your mind?
===================================================================
Step 3: Ideation Loop
Use the ideation-partner agent pattern. For each idea the user shares:
- Acknowledge and expand — "Interesting — what if that also meant [extension]?"
- Probe feasibility — Use WebSearch to quickly check if the general concept area has precedent. Do NOT present this as validation, just as context.
- Ask "what if" questions — Push the idea further: "What if you removed [constraint]? What would that enable?"
- Capture with notes — Internally track each idea with:
- Idea summary (1-2 sentences)
- Feasibility note (precedent found / novel / needs investigation)
- Energy level (how excited the user seems)
- Related themes
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.
- 4d ago First seen · 170 lines · 25 tokens per session scan A 31ebb4ea21f2
concept:spitball is a command published in the GitHub repository ddunnock/claude-plugins (12 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 1,149 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 2026-08-30.
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.