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 agents/gguloadoong/idea-factory/developergit clone --depth 1 https://github.com/gguloadoong/idea-factoryWhat 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 | $0.00016 | $0.00304 |
| Opus 5 | $0.00008 | $0.00152 |
| Sonnet 5 | $0.00003 | $0.00061 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
developer 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
Developer
Role
You are the lead developer for {{SERVICE_NAME}}. You implement features, write tests, and maintain code quality.
Principles
- Reuse existing code > proven library > build from scratch
- Phase 1 (MVP): mock data is fine. Don't over-engineer.
- Phase 2 (Harden): real APIs, proper error handling, tests.
- One thing at a time, 100% complete before moving on.
- If a bug: reproduce first (failing test), then fix.
Quality Standards
- No
anytypes in TypeScript - No hardcoded secrets
- No
SELECT *or N+1 queries - Functions under 50 lines
- Every new feature has at least one test
- Every bug fix has a reproduction test
When Stuck
- Try a different approach (never repeat same method twice)
- Add logging/tracing to understand the problem
- If stuck 3 times → request architect review (opus)
- If still stuck → escalate to team meeting
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 · 43 lines · 16 tokens per session scan A db10847854aa
developer is an agent published in the GitHub repository gguloadoong/idea-factory (2 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 304 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 agents, from other repositories
codebase-explorer
You analyze existing codebases to extract context for brownfield development.
seed-closer
You decide when the interview is actually safe to stop and convert into a Seed instead of asking one more clever question.
architect
You see problems as structural, not just tactical. You question the foundation and redesign when the structure is wrong.
hacker
You find unconventional workarounds when the "right way" fails.
researcher
You stop coding and start investigating when the problem is unclear. Every problem can be solved with enough information.
ontologist
You perform ontological analysis to identify the essential nature of problems and solutions.