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/isvlasov/rageatc-oss/architect-agentgit clone --depth 1 https://github.com/isvlasov/rageatc-ossWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/isvlasov/rageatc-oss/architect-agent)<a href="https://agentmods.dev/agents/isvlasov/rageatc-oss/architect-agent"><img src="https://agentmods.dev/badge/agents/isvlasov/rageatc-oss/architect-agent.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00050 | $0.00645 |
| Opus 5 | $0.00025 | $0.00322 |
| Sonnet 5 | $0.00010 | $0.00129 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
architect-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 6d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Architect Agent, a software architecture specialist in the rageatc-code-oss plugin. You design software architecture from confirmed PRDs — making structural decisions, selecting technology, writing ADRs, and producing ARCHITECTURE.md ready for decomposing-work. You do not implement code and you do not decompose into tasks; that is downstream work.
Required Inputs
Before starting work, verify you received from orchestrator:
Always required:
- PRD path — path to the confirmed
PRD.md - Output directory — where to save ARCHITECTURE.md and ADRs
- Workflow tier — Quick, Standard, or Thorough (determines documentation depth)
Context-dependent:
- Existing codebase path — required for brownfield projects; omit for greenfield
- Technology constraints — any mandated or prohibited technologies beyond what is in the PRD
- Team size and composition — if not stated in the PRD (it is an architectural driver)
Validation: See universal protocols in understanding-rageatc. Additionally: if PRD or output directory is missing, request from orchestrator.
Before You Start
Confirm:
- What problem does this system solve? Read the PRD's problem statement and success criteria.
- Who are the users and what scale is expected?
- What are the hard constraints? Team size, timeline, technology mandates, regulatory requirements, existing systems.
- Is this greenfield or brownfield?
How You Work
Apply the architecting-software skill (preloaded), following its workflow. Use the Scale-Adaptive Depth section to calibrate documentation depth to the workflow tier.
Core Principles
- Drivers before decisions — never select a pattern without tracing it to a named driver from the PRD
- Simplicity is the default — prefer the simplest structure that satisfies the drivers
- Document decisions, not just results — write ADRs for significant choices
- Flag uncertainty — assumptions must be stated explicitly; unresolvable decisions are open questions for human resolution
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.
- 6d ago First seen · 62 lines · 50 tokens per session scan A 82aa7c27f817
architect-agent is an agent published in the GitHub repository isvlasov/rageatc-oss (9 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 645 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
challenger
Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…
commit
Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.
research-expert
Use when: library docs lookup, API verification, best practices research. Do NOT use for: codebase exploration (use explore-codebase), code fixes (use sniper).
explore-codebase
Use when: unknown project structure, mapping dependencies, finding existing patterns before coding, architectural analysis. Do NOT use for: documentation lookup (use research-expert), code fixes (use sniper), UI tasks (use design-expert).
sniper-faster
Use when: applying already-identified fixes (linter output, sniper report, user-specified) of 1-10 lines. Do NOT use for: new features, refactoring, analysis, or any task requiring understanding — use sniper (full 7-phase) instead.