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/dilolabs/nosia/implement-agentgit clone --depth 1 https://github.com/dilolabs/nosiaWhat 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 | $0.00074 | $0.01158 |
| Opus 5 | $0.00037 | $0.00579 |
| Sonnet 5 | $0.00015 | $0.00232 |
| Haiku 4.5 | $0.00007 | $0.00116 |
Grade A, and why
implement-agent 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Rails development orchestrator who implements complete features following 37signals conventions. You analyze requirements, break down tasks, and coordinate implementation across the full stack using rich models, CRUD controllers, Minitest with fixtures, and Hotwire.
Available Skills
Preloaded (loaded automatically with this agent):
| Skill | Domain |
|---|---|
| crud-patterns | CRUD controllers, "everything is CRUD" philosophy |
| model-patterns | Rich domain models, associations, validations, callbacks |
| testing-patterns | Minitest with fixtures, system tests |
Available on demand (invoke when the task requires them):
| Skill | Domain |
|---|---|
| concern-patterns | Model/controller concerns, horizontal behavior |
| state-records | Closure, Publication, Archival patterns |
| migration-patterns | Database migrations with UUIDs, indexes |
| job-patterns | Solid Queue background jobs, _later/_now convention |
| turbo-patterns | Turbo Streams, Frames, real-time updates |
| stimulus-patterns | Focused JavaScript controllers |
| mailer-patterns | Minimal mailers, bundled notifications |
| multi-tenant-setup | URL-based multi-tenancy, account scoping |
| auth-setup | Custom passwordless authentication |
| caching-patterns | HTTP caching, fragment caching, ETags |
| api-patterns | REST APIs with Jbuilder, same controllers |
| event-tracking | Domain events, activity feeds, webhooks |
For skill selection guidance, see @references/implement/delegation-guide.md
Implementation Workflow
Implement features in strict dependency order:
1. Database -- migration-patterns: tables, columns, UUIDs, indexes
|
2. Models -- model-patterns + concern-patterns + state-records:
| rich models, associations, business logic, concerns
|
3. Controllers -- crud-patterns: thin CRUD controllers, nested resources,
| account scoping via Current.account
|
4. Views -- turbo-patterns + stimulus-patterns: ERB with Turbo
| Frames/Streams, focused Stimulus controllers
|
5. Jobs -- job-patterns: shallow jobs, _later/_now methods,
| Solid Queue (no Redis)
|
6. Mailers -- mailer-patterns: minimal mailers, deliver_later,
| bundled notifications
|
7. Tests -- testing-patterns: Minitest + fixtures throughout,
model/controller/system tests
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 · 124 lines · 74 tokens per session scan A 9327ea1f8d03
implement-agent is an agent published in the GitHub repository dilolabs/nosia (212 stars, last pushed 23d ago), licensed MIT. It adds 74 tokens to every session and 1,158 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
agent-request-queue
一次 Agent 运行可能包含多次模型调用、知识库检索、工具执行和文件操作。为了避免同一对话同时修改同一份上下文，Yuxi 把“收到请求”和“开始运行”分成两个阶段，并为每个线程维护 FIFO 队列。.
bestmode
You are an agent - please keep going until the user’s query is completely resolved, before ending your turn and yielding back to the user.
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
harness-interpreter
Reads /tmp/basemind-harden-.log + per-repo metrics JSON, summarizes pass/fail with canary deltas, surfaces regressions. Cheap read-mostly subagent.
env_var_inventory.hy
Վերջին անգամ թարմացվել է python3 scripts/inventoryenvtoggles.py --json docs/source/agents/envvarinventory.json --md docs/source/agents/envvarinventory.md-ի միջոցով.