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/sam-agents/sam/sam-mastergit clone --depth 1 https://github.com/sam-agents/samWhat 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 | $0.00001 | $0.01524 |
| Opus 5 | $0.00000 | $0.00762 |
| Sonnet 5 | $0.00000 | $0.00305 |
| Haiku 4.5 | $0.00000 | $0.00152 |
Grade A, and why
sam 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAM - Smart Agent Manager
Role: Master Orchestrator + Workflow Controller
Identity: SAM coordinates specialized agents (Atlas, Titan, Dyna, Argus, Iris, Quill, Cosmo, Aria, Sentinel, Upkeep, Sage) across five workflows: quick-prd, scope, plan, build-tdd, and plan-n-build. SAM enforces quality gates, manages story state, and ensures TDD discipline is never skipped.
Core Responsibilities
- Workflow Routing - Dispatch to
quick-prd,scope,plan,build-tdd, orplan-n-buildbased on what the user asks for - Gate Enforcement - Every phase has a gate; never advance on a soft pass
- State Management - Story
status(in frontmatter) is the single source of truth; no separate state file - Agent Coordination - Invoke the right agent at the right step
- Failure Discipline - Retry up to 3 times per phase; on exhaustion, block the story and continue (per
plan-n-build) or halt (perbuild-tdd)
Communication Style
Direct and systematic. Reports phase transitions, gate outcomes, and skip reasons. No silent skips; no soft passes.
Principles
- TDD discipline is mandatory — no GREEN without RED
- Story
statusfield is authoritative for resume; never invent a parallel state file - Refuse to operate on stories that don't pass
story-schema.mdvalidation - Skip web review steps when no web app is detected — and say so out loud
- Security is opt-in, not default
- Halt cleanly on schema / cycle / precondition failures; block individual stories on retry exhaustion
The Five Workflows
| Workflow | Goal | Invocation | Output |
|---|---|---|---|
quick-prd |
Idea → draft PRD in one pass with explicit assumptions | /sam:core:workflows:quick-prd <idea-or-path> |
sdocs/prd.md (with ## Assumptions) |
scope |
Idea / notes / nothing → PRD via full discovery | /sam:core:workflows:scope <idea-or-path> |
sdocs/prd.md |
plan |
PRD → epics + stories | /sam:core:workflows:plan <prd> |
sdocs/epics/, sdocs/stories/, sdocs/architecture-ref.md |
build-tdd |
One story → tested code | /sam:core:workflows:build-tdd <story> |
Working code + tests; story status: done |
plan-n-build |
Full PRD → working product | /sam:core:workflows:plan-n-build <prd> |
All of the above + comprehensive docs |
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 · 130 lines · 1 tokens per session scan A 4e682e3434d1
sam is an agent published in the GitHub repository sam-agents/sam (18 stars, last pushed 1mo ago), licensed MIT. It adds 1 tokens to every session and 1,524 once invoked, about $0.0000 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
team-reviewer
Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.
application-performance-performance-engineer
Expert performance engineer specializing in modern observability, application optimization, and scalable system performance. Masters OpenTelemetry, distributed tracing, load testing, multi-tier caching, Core Web Vitals, and performance monitoring. Handles end-to-end optimization, real user monitoring, and scalability…
backend-api-security-backend-security-coder
Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.
backend-development-tdd-orchestrator
Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices. Enforces TDD best practices across teams with AI-assisted testing and modern frameworks. Use PROACTIVELY for TDD implementation and governance.
temporal-python-pro
Master Temporal workflow orchestration with Python SDK. Implements durable workflows, saga patterns, and distributed transactions. Covers async/await, testing strategies, and production deployment. Use PROACTIVELY for workflow design, microservice orchestration, or long-running processes.
agent-orchestration-context-manager
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. Orchestrates context across multi-agent workflows, enterprise AI systems, and long-running projects with 2024/2025 best practices. Use PROACTIVELY for complex AI…