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/kesteva/soloflow/idea-extractorgit clone --depth 1 https://github.com/kesteva/soloflowWhat 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 | $0.00012 | $0.00459 |
| Opus 5 | $0.00006 | $0.00230 |
| Sonnet 5 | $0.00002 | $0.00092 |
| Haiku 4.5 | $0.00001 | $0.00046 |
Grade A, and why
idea-extractor 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.
What it actually says
/soloflow:idea-extractor
Phase 1 of the SoloFlow pipeline. Turns raw input into a structured idea file (with codebase grounding and optional external research) and offers to refine it into execution-ready plans.
This command is a preconfigured wrapper for /soloflow:planner. The unified planner is the canonical entry; this wrapper exists for users who want the focused single-idea flow without seeing the open prompt.
The user's input is: $ARGUMENTS
Step 1: Dispatch into the unified planner
Read ${CLAUDE_PLUGIN_ROOT}/commands/planner.md with the Read tool and execute its procedure end-to-end with $ARGUMENTS rebound to:
--mode=single-idea $ARGUMENTS
That is, prepend the literal token --mode=single-idea followed by a single space, then the original $ARGUMENTS. The planner's Step 0.5 (Mode resolution) detects the token, strips it, and routes directly into Phase 1a (single-idea extract). Phase 1a behaves identically to this command's historical surface: clarify if ambiguous, extract via the idea-extractor agent, optional research, human checkpoint, commit, then prompt to refine into tasks. On Refine now the planner falls through to Phase 2; on Not yet it stops with a deferred-commands hint.
Do NOT re-run any of the planner's earlier steps independently — treat the planner's instructions as a continuation of this run.
Notes
- For multi-item capture, use
/soloflow:braindump(also a thin wrapper). - For refining an existing IDEA, use
/soloflow:planner IDEA-NNNdirectly — no need to go through this wrapper. - The unified
/soloflow:planner(with no args) opens with a mode picker; it's the canonical entry when you're not sure which path you need.
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 · 36 lines · 12 tokens per session scan A f88da8753f7a
idea-extractor is a command published in the GitHub repository kesteva/soloflow (40 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 459 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.
constitution
Create or update the project constitution from interactive or provided principle inputs.