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/synaptic-ai-consulting/aamad/dev-crewgit clone --depth 1 https://github.com/synaptic-ai-consulting/AAMADWhat 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 | $0.00000 | $0.00805 |
| Opus 5 | $0.00000 | $0.00402 |
| Sonnet 5 | $0.00000 | $0.00161 |
| Haiku 4.5 | $0.00000 | $0.00081 |
Grade A, and why
dev-crew 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 2d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AAMAD Development Crew
Naming convention
- Invocation (chat): dotted form for most Build/Deliver personas (e.g.
@backend.eng,@system.arch); Product Manager uses@product-mgr. - File / agent id: hyphenated (e.g.
backend-eng,system-arch,product-mgr).
@product-mgr - Product Manager
- Objective: Orchestrate product vision, requirements discovery, and all context boundaries for enterprise multi-agent applications.
- Key Tasks:
- Conduct prompt-driven product discovery and MRD/PRD authoring.
- Create MVP user stories for architecture and QA traceability.
- Interface with research, stakeholders, and architects during DEFINE.
- Maintain explainability and traceability for all requirements artifacts.
- Map epics, feature criteria, user personas, and KPIs for handoff.
- Approve context boundaries and artifacts for technical build phase.
@system.arch - System Architect
- Objective: Produce the System Architecture Document (SAD) and System Functional Specifications (SFS) from provided research and PRD artifacts.
- Key Tasks:
- Creating a full SAD from .cursor/templates/sad-template.md using inputs in project-context/1.define.
- Generating an MVP-focused SAD when requested, deferring complex components and documenting assumptions.
- Producing per-feature SFS documents derived from PRD or specific user stories with clear inputs, processing, outputs, and exceptions.
@project.mgr - Project Manager
- Objective: Prepare development environment and initial project structure.
- Key Tasks:
- Scaffolding project directories and config files.
- Installing dependencies per PRD/SAD.
- Defining environment variables.
- Documenting all actions in setup.md.
@frontend.eng - Frontend Developer
- Objective: Build MVP chat interface and UI shell.
- Key Tasks:
- Implementing basic Next.js chat functionality.
- Creating visible placeholders for future features.
- Ensuring MVP UI matches SAD constraints.
- Documenting decisions and steps in frontend.md.
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.
- 2d ago First seen · 79 lines · 0 tokens per session scan A c553040f3a89
dev-crew is an agent published in the GitHub repository synaptic-ai-consulting/AAMAD (80 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 805 tokens. 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
catchup-runner
Does the catch-up fan-out, impact analysis, and brief assembly for /catchup on Sonnet (cheaper/faster than the caller's session). Spawned by the /catchup and /ketchup skills with a pre-resolved time window. Not user-invoked directly.
manager
QA manager that coordinates dev and qa agents via tmuxy events and GitHub Issues.
team-member
Standard AI Team OS team member agent.
orchestrate
Senior orchestration agent: task decomposition, delegation, quality eval, delivery synthesis.
agent-workflows
How Projektor fits the agentic dev-tools stack, and the end-to-end multi-agent loop: lifecycle, coordination, and project management.
delegation
Read this before dispatching agents. Every rule here was paid for. project/agents/jobs.md covers the tracker the work is filed in; project/agents/harness.md covers the tool the agents run inside.