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/rchase999/aidd/ideategit clone --depth 1 https://github.com/rchase999/aiddWhat 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 | $0.00024 | $0.01115 |
| Opus 5 | $0.00012 | $0.00558 |
| Sonnet 5 | $0.00005 | $0.00223 |
| Haiku 4.5 | $0.00002 | $0.00112 |
Grade A, and why
ideate 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 1 — Ideate
Load the aidd-core skill for the phase contract.
Raw idea: $ARGUMENTS
Ensure the workspace exists (mode is auto-detected from what is already in the directory):
!node "${CLAUDE_PLUGIN_ROOT}/scripts/aidd.mjs" init 2>&1
If the mode above says brownfield
This directory already holds a project, so phase 1 changes shape. You are not inventing a product — you are scoping a change to something that exists and has users.
- Dispatch the
aidd-surveyoragent first. Do not ask the user what stack they are on; the code knows, and asking wastes their time and yours. - While it runs, ask what the change is for — same sharpening instinct, different subject.
- The brief becomes a change brief (structure below), and the stack is recorded as fact, not proposed as an option.
The "no technology" rule below is about not choosing technology prematurely. Naming what is already installed is reporting, not choosing — do that freely.
What this phase is for
Take a fuzzy idea and make it clear — not bigger. The user has a picture in their head that is sharper than the sentence they typed. Your job is to pull that picture into focus and write it down.
Hard limits
- No technology. No frameworks, languages, databases, hosting, or libraries. That is phase 2's job and naming a stack here quietly decides it.
- No feature list. Do not brainstorm what it could do. One idea does one job.
- No roadmap, no phases, no monetisation, no scale plan unless the user raises them.
- At most 2 rounds of questions, 3 questions per round, via
AskUserQuestion. If the user answers "you decide", decide and move on. - Keep your own prose short. The user came with an idea, not for an essay.
What to actually do
- Read the raw idea back in one sentence, sharper than they wrote it. If you got it wrong they will correct you immediately — that is the cheapest possible signal.
- Offer direction, not decisions: 2–4 short framings of what this idea could be at its core (e.g. "a logbook that happens to predict" vs "a predictor that happens to log"). These are angles on the same idea, not different products.
- Ask the sharpening questions that actually change the shape of the thing. Good ones:
- Who is the one person this is for, and what were they doing five minutes before they opened it?
- What is the single moment where this earns its keep?
- What is the nearest thing that already exists, and what about it annoys them?
- What must it not become?
- Write
.aidd/01-ideate/brief.md.
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 · 116 lines · 24 tokens per session scan A 6f44414a1075
ideate is a command published in the GitHub repository rchase999/aidd (2 stars, last pushed 24d ago), licensed MIT. It adds 24 tokens to every session and 1,115 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
loop
Iteratively fix issues until all resolved or max iterations reached.
feature
Create a feature specification using spec-driven development.
quality-gate
Command "quality-gate" from VoDaiLocz/kilo-kit-mcp, covering ✅ quality gate command, workflow, gates, gate 1: pre-execution and gate 2: per-behavior.
memory
Search, store, and manage AI Team Memory — agent expertise, decisions, learnings, and code patterns. File-based by default, with an optional memory MCP overlay.
deep-audit.skeleton
Aciklama: Bu bolum Bootstrap tarafindan manifest verileriyle doldurulur. Gerekli manifest alanlari: project.description, stack.primary, project.structure, project.subprojects, stack.orm, stack.authmethod Ornek cikti.
do-it-retrospective
开关本项目的本地行为反馈记录，或输出已记录问题的去敏复盘报告。参数为 on / off / status / report。.