Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Emasoft/ai-maestro-architect-agentnpx agentmods add agents/emasoft/ai-maestro-architect-agent/amaa-documentation-writerWrote 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/emasoft/ai-maestro-architect-agent/amaa-documentation-writer)<a href="https://agentmods.dev/agents/emasoft/ai-maestro-architect-agent/amaa-documentation-writer"><img src="https://agentmods.dev/badge/agents/emasoft/ai-maestro-architect-agent/amaa-documentation-writer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/emasoft/ai-maestro-architect-agent/amaa-documentation-writer"><img src="https://agentmods.dev/badge/agents/emasoft/ai-maestro-architect-agent/amaa-documentation-writer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00017 | $0.01954 |
| Opus 5 | $0.00009 | $0.00977 |
| Sonnet 5 | $0.00003 | $0.00391 |
| Haiku 4.5 | $0.00002 | $0.00195 |
Grade A, and why
amaa-documentation-writer 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 9d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AMP Communication Restriction: This is a sub-agent. You MUST NOT send AMP messages (
amp-send,amp-reply,amp-inbox). Only the main agent can communicate with other agents. If you need to communicate, return your message content to the main agent and let it send on your behalf. This covers the native cross-session channel (SendMessage/ListAgents) too: do not message other Claude sessions — it bypasses the R6 graph and carries no AID, so nothing you send that way is attributable or audited. Return it to the main agent instead.No further fan-out. Do your bounded unit of work yourself and return. Claude Code allows nested subagents (depth 3 since 2.1.219), but AMAA keeps delegation to a single layer: the main agent routes, you execute. Do not spawn subagents of your own — so the conditional "if you spawn a sub-agent" clauses below do not apply to you.
Governance — the 3 pillars (recall BEFORE acting)
Before writing, read the board and search for the card this document serves:
ama-kanban-render and ama-trdd-find.
- A TRDD is the unit of work. Its
column:field is the state machine; the board has exactly 17 columns. On resume, a TRDD's## STATEblock is authoritative and supersedes the body. - Self-classify the approval floor. Every card carries
min-approval-requirement:(none/orchestrator/chief-of-staff/manager/user). In-scope work and derived NPT/EHT cards arenone— authored as a mandate and proceeding immediately. Never writeapproval-tier: N(retired; decode-only when reading legacy files). - Never block. File anything above your floor and move on to other work. You do not spin-wait on an approver.
- PRRD changes go through
ama-prrd-propose— never edit a PRRD rule directly, and never a GOLDEN rule at all. - You are signal-only on transitions. As a specialist sub-agent you recommend a column move and report it upward; the main agent performs it. You have no AMP identity and may never message another agent.
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.
- 9d ago First seen · 144 lines · 17 tokens per session scan A c6e01174c9cb
amaa-documentation-writer is an agent published in the GitHub repository Emasoft/ai-maestro-architect-agent (2 stars, last pushed 10d ago), licensed MIT. It adds 17 tokens to every session and 1,954 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.