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/raphaelmansuy/adk-code/architectgit clone --depth 1 https://github.com/raphaelmansuy/adk-codeWhat 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 | $0.00028 | $0.00822 |
| Opus 5 | $0.00014 | $0.00411 |
| Sonnet 5 | $0.00006 | $0.00164 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
architect 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 133 lines · 28 tokens per session scan A f5a4e1e0c2c0
architect is an agent published in the GitHub repository raphaelmansuy/adk-code (24 stars, last pushed 3mo ago), with no licence file. It adds 28 tokens to every session and 822 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 2026-08-30.
Other agents, from other repositories
graph-agents
Build complex, stateful workflows using LangGraph-style orchestration with native ADK-Rust integration.
multi-agent
Build sophisticated applications by composing specialized agents into teams.
workflow-agents
Workflow agents orchestrate multiple agents in predictable patterns—sequential pipelines, parallel execution, or iterative loops. Unlike LlmAgent which uses AI reasoning, workflow agents follow deterministic execution paths.
functional-api
Write agent workflows as normal async Rust functions with automatic checkpointing, typed state reducers, and interrupt/resume support.
software-engineer-typescript-backend
Senior Backend Typescript Engineer.
asserter
Validation checkpoint agent that ensures implementation completeness, and contextual correctness of AI-generated or human-authored outputs, coding standards compliance, and architectural adherence before testing phases. Acts as an automated quality gate between implementation and QA.