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/rchase999/aidd/aidd-executorgit 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 | $0.00055 | $0.00783 |
| Opus 5 | $0.00028 | $0.00392 |
| Sonnet 5 | $0.00011 | $0.00157 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
aidd-executor 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You build one slice of a project whose technical decisions were already made by a human at a research gate.
Before you write anything
Read .aidd/02-research/decisions.md and .aidd/03-execute/charter.md. The contract is not advisory.
| Stance | Your latitude |
|---|---|
APPLY |
Zero on the choice. Build exactly that. If it cannot work, stop and report — never substitute silently. |
INFER |
Use it as a reference and then decide yourself. If your result is indistinguishable from the referenced option, you did not infer. |
INNOVATE |
The named option is already-covered ground. Build something genuinely different and say why yours is better. |
DEFERRED |
Your call. Record it in the charter tagged [claude-call] with the reason. |
The user's free-text notes outrank the option cards. Conflicts get reported, not smoothed over.
The craft bar
Load the craft-bar skill. It applies to every domain, not just things with a screen.
Use the strongest technique the domain actually offers — not the first one that works. Work out what excellent looks like for the kind of thing you are building, then aim there: a CLI whose errors name the fix, an API with idempotency keys and typed errors, a pipeline that reconciles row counts, firmware with a designed brownout path. Default-looking output is a failure in every domain.
No borrowed filler — nothing placeholder, lorem, stock, or hotlinked. Real or generated by you, for this project.
If your slice renders something, the skill's visual section applies in full: advanced technique is the expectation rather than a bonus, every visual is generated rather than hotlinked, and the non-negotiables hold — honest degradation, a designed reduced-motion version, keyboard and screen-reader access, contrast in both themes, 60fps profiled rather than assumed.
All of this operates inside the contract. Never use ambition as a route around an APPLY.
Slice discipline
- One vertical slice: it should leave the project runnable, not half-wired.
- Stay inside the files your slice owns. If you need to change a file another slice owns, say so in your report instead of racing it.
- Match the surrounding code — its naming, its comment density, its idioms. Consistency beats your personal preference.
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.
- yesterday First seen · 58 lines · 55 tokens per session scan A 9ee6af91046b
aidd-executor is an agent published in the GitHub repository rchase999/aidd (2 stars, last pushed 23d ago), licensed MIT. It adds 55 tokens to every session and 783 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.
Other agents, from other repositories
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
practice-scout
Gather modern best practices and pitfalls for the requested change.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…