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 skills/aegntic/compound-engineering/ideatenpx skills add aegntic/compound-engineering --skill ideategit clone --depth 1 https://github.com/aegntic/compound-engineeringWhat 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 | $0.00019 | $0.03107 |
| Opus 5 | $0.00010 | $0.01554 |
| Sonnet 5 | $0.00004 | $0.00621 |
| Haiku 4.5 | $0.00002 | $0.00311 |
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 — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ideate
Generate improvement ideas that are grounded in the actual repository, reject weak ones aggressively, and preserve the strongest survivors in docs/ideation/ before handing one off to /workflows:brainstorm.
Use this when the user wants the AI to suggest what to improve rather than refine an idea they already chose.
ideateanswers: "What are the strongest ideas worth exploring?"/workflows:brainstormanswers: "What exactly should one chosen idea mean?"/workflows:plananswers: "How should it be built?"
This workflow produces a ranked ideation artifact in docs/ideation/. It does not produce requirements, plans, or code.
Interaction Method
Use the platform's blocking question tool when available (AskUserQuestion in Claude Code, request_user_input in Codex, ask_user in Gemini). Otherwise, present numbered options in chat and wait for the user's reply before proceeding.
Ask one question at a time. Prefer concise single-select choices when natural options exist.
Focus Hint
Interpret any provided argument as optional context. It may be:
- a concept such as
DX improvements - a path such as
plugins/compound-engineering/skills/ - a constraint such as
low-complexity quick wins - a volume hint such as
top 3,100 ideas, orraise the bar
If no argument is provided, proceed with open-ended ideation.
Core Principles
- Ground before ideating - Scan the actual codebase first. Do not generate abstract product advice detached from the repository.
- Diverge before judging - Generate the full idea set before evaluating any individual idea.
- Use adversarial filtering - The quality mechanism is explicit rejection with reasons, not optimistic ranking.
- Preserve the original prompt mechanism - Generate many ideas, critique the whole list, then explain only the survivors in detail.
- Use agent diversity to improve the candidate pool - Parallel sub-agents are a support mechanism for richer idea generation and critique, not the core workflow itself.
- Preserve the artifact early enough - Before any handoff or session end, write the ideation document so the work survives interruptions.
- Route action into brainstorming - Ideation identifies promising directions;
/workflows:brainstormdefines the selected one precisely enough for planning.
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 · 349 lines · 19 tokens per session scan A 2a510edc6471
ideate is a skill published in the GitHub repository aegntic/compound-engineering (2 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 3,107 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 skills, from other repositories
a2ui-renderer
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…
copilotkit-develop
Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.
recon
Codebase reconnaissance agent for Bug Hunter. Maps architecture, identifies trust boundaries, classifies files by risk priority, and detects service boundaries. Does NOT find bugs — finds where bugs hide.
standards
Runs Phase 4 review/publish/verify for a cli-web- CLI: implementation review by 3 parallel agents, the tiered quality checklist (Tier 1 critical fail-fast, then comprehensive), pip install + smoke test, and per-CLI skill generation. Use when a CLI's tests pass and it is ready to be validated and published.
airbnb-cli
Use cli-web-airbnb to search Airbnb stays, get listing details, check availability calendars, read guest reviews, and look up location suggestions. Invoke this skill whenever the user asks about Airbnb accommodations, vacation rentals, listing prices, availability, guest reviews, or wants to search for places to stay.…
notebooklm-cli
Drives Google NotebookLM via the cli-web-notebooklm command-line tool — create and manage notebooks, add URL/text sources, ask questions grounded in the sources, and generate/download artifacts (audio overview, video, slide deck, mindmap, study guide, quiz, FAQ, briefing, infographic, data table). Use when the user…