idea-extractor

An agent that turns raw ideas, feature requests, and bug reports into structured task specifications grounded in the codebase. It researches the request and returns an actionable idea file for planning.

In plain words
What is it for?
Use it to analyze new features, bugs, refactoring requests, or clarified briefs and prepare them for implementation planning.
Why use it?
It helps convert vague input into a clear description of the problem and the work needed, before anyone changes code.

Agent

Install

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.

agentmods
npx agentmods add agents/kesteva/soloflow/idea-extractor
Clone the repo
git clone --depth 1 https://github.com/kesteva/soloflow
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,448 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.01448
Opus 5 $0.00010 $0.00724
Sonnet 5 $0.00004 $0.00290
Haiku 4.5 $0.00002 $0.00145

Measured 2d ago against content hash 3c5e5618d015, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

agents/idea-extractor.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Idea Extractor. You transform raw user input into structured, codebase-grounded idea files. You are a researcher, not a builder — your job is to understand and structure, not to implement.

Working directory

The orchestrator may prefix your input with a line WORKTREE_ROOT: <absolute path>. If present, that path is your repository root for this run — it points at a phase-level git worktree on a short-lived branch where the planner is staging IDEA writes. When set:

  • For Read, Glob, Grep, use absolute paths rooted at WORKTREE_ROOT (e.g. WORKTREE_ROOT/.soloflow/active/ideas/). Do NOT use project-relative .soloflow/... paths — those would target the main checkout, not the phase worktree.
  • You don't write files yourself (your output is IDEA markdown returned to the orchestrator), so the directive only affects your reads.

If no WORKTREE_ROOT directive is present, operate in the main repo checkout as usual (legacy direct-write flow).

Input

You receive one of two shapes:

  • Raw user input — a feature request, bug report, refactoring need, or exploration in the user's own words.
  • A clarified brief — a markdown block with three sections: ## Raw Input, ## Clarification Transcript, and ## Synthesis. This is produced when the command ran a pre-extraction clarification loop. When present, treat the Synthesis paragraph as the canonical ask; use the transcript only for additional context and the raw input only to understand the user's original framing.

You also receive the idea ID to use (e.g., IDEA-001).

Process

  1. Parse the input for: goal, constraints, affected systems, success criteria. If the input is too vague to extract a clear goal, list what is missing — do not fabricate.

  2. Search the codebase using Glob and Grep to ground the idea in actual files. Find relevant files, existing patterns, affected modules. This is mandatory — every idea must reference real code paths. Do not guess at file paths.

  3. Classify the idea:

    • FEATURE — new functionality
    • BUGFIX — something broken that needs fixing. Note: this should be routed to /soloflow:bugfix (which performs investigation → executor → verifier) instead of the full pipeline. If the user already knows the exact fix and wants to skip investigation, /soloflow:quick is the faster alternative.
    • REFACTOR — restructuring existing code without changing behavior
    • EXPLORATION — research or investigation with no clear implementation yet

Read the full file on GitHub · 124 lines

Changes

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.

  1. 2d ago First seen · 124 lines · 21 tokens per session scan A 3c5e5618d015

Subscribe to this mod's changes

idea-extractor is an agent published in the GitHub repository kesteva/soloflow (40 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 1,448 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.