ideation

A command that analyzes a project for possible improvements across code, quality, documentation, security, performance, and user experience. It uses Git history, competitive research, and interactive HTML reports.

In plain words
What is it for?
Use it to run or filter an ideation review, inspect its status, accept or dismiss suggestions, and create one or more GitHub issues.
Why use it?
It turns broad improvement ideas into findings that you can review, accept, dismiss, or turn into GitHub issues.

Command

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 commands/bvdr/claude-plugins/ideation
Clone the repo
git clone --depth 1 https://github.com/bvdr/claude-plugins
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,218 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 $0.00053 $0.06218
Opus 5 $0.00026 $0.03109
Sonnet 5 $0.00011 $0.01244
Haiku 4.5 $0.00005 $0.00622

Measured yesterday against content hash 8cfeab6d1ce2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ideation 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 yesterday.

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.

plugins/bvdr-ideation-and-roadmap/commands/ideation.md · 632 lines

How it starts

The opening of the file, as written. The whole thing — 632 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ideation Orchestrator

You are the orchestrator for the Ideation system. You run autonomously and handle all subcommands. Read this entire file before taking any action.


Step 0: Parse Arguments

Read the skill args string and determine the subcommand and flags.

Subcommand detection (first non-flag token):

Args Subcommand
(empty or no non-flag tokens) run
help help
accept <id> [<id>...] accept
dismiss <id> [--reason "..."] dismiss
status status
create-issues create-issues
create-issue <id> create-issue

Flag detection (can appear alongside run):

  • --only type1,type2 → set FILTER_TYPES (parse comma-separated list, resolve aliases — see alias table below)
  • --refresh → set FORCE_REFRESH = true
  • --no-open → set NO_OPEN = true

Alias table for --only:

Alias Full slug
ci code-improvements
cq code-quality
doc documentation
sec security
perf performance
ux ui-ux

If the value already contains a dash (e.g., code-improvements) treat it as a full slug directly.

Once you know the subcommand, jump to that section below.


Subcommand: help

Print this exact text and stop — do not run any other phase:

IDEATION - AI-powered project improvement analysis

USAGE:
  /ideation                              Run all 6 ideation types
  /ideation --only type1,type2           Run specific types (see below)
  /ideation --refresh                    Force re-run deep analysis
  /ideation --no-open                    Don't auto-open HTML report
  /ideation help                         Show this help

REVIEW:
  /ideation accept <id> [<id>...]        Mark ideas as accepted
  /ideation dismiss <id> [--reason ""]   Mark idea as dismissed
  /ideation status                       Show review summary

GITHUB:
  /ideation create-issues                Create GH issues for all accepted
  /ideation create-issue <id>            Create GH issue for specific idea

IDEATION TYPES (use with --only, comma-separated):
  code-improvements   Pattern extensions and architecture opportunities
  code-quality        Refactoring, code smells, complexity
  documentation       Missing docs, API docs, inline comments
  security            OWASP, secrets, auth, input validation
  performance         Bundle size, N+1 queries, memory, caching
  ui-ux               Accessibility, consistency, responsiveness

  Short aliases: ci, cq, doc, sec, perf, ux
  Example: /ideation --only sec,perf

OUTPUT:
  .claude/ideation/ideation-N/report.html   Interactive HTML report (N auto-increments)
  .claude/ideation/ideation-N/ideation.json Machine-readable results
  .claude/ideation/deep-analysis.json       Cached deep analysis (shared across runs)

Read the full file on GitHub · 632 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. yesterday First seen · 632 lines · 53 tokens per session scan A 8cfeab6d1ce2

Subscribe to this mod's changes

ideation is a command published in the GitHub repository bvdr/claude-plugins (3 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 6,218 once invoked, about $0.0003 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.