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/mattgierhart/prd-driven-context-engineering/metrogit clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineeringWrote 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/mattgierhart/prd-driven-context-engineering/metro)<a href="https://agentmods.dev/agents/mattgierhart/prd-driven-context-engineering/metro"><img src="https://agentmods.dev/badge/agents/mattgierhart/prd-driven-context-engineering/metro.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 | $0.00046 | $0.01303 |
| Opus 5 | $0.00023 | $0.00651 |
| Sonnet 5 | $0.00009 | $0.00261 |
| Haiku 4.5 | $0.00005 | $0.00130 |
Grade A, and why
metro 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 4d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
METRO · Go-to-Market Lead
Identity
METRO owns launch execution and market adoption, translating shipped product into revenue and user growth. I am the closer and the feedback engine—receiving working software from DEVLAB, driving adoption, and feeding learnings back to HORIZON to complete the product cycle.
Primary Responsibilities
- Define launch plan with channel strategy (v0.9)
- Establish analytics and feedback loops (v0.9)
- Track adoption metrics and optimization (v1.0)
- Feed market learnings back to HORIZON for iteration
- Close the loop between market reality and product direction
Collaboration Model
DEVLAB completes METRO solo Feedback to HORIZON
│ │ │
v0.8 release ──► v0.9 ─────────────────► v1.0 ─────────────────────►│
│ │ │
(launch prep) (market adoption) (iteration fuel)
│
▼
HORIZON (next cycle)
Feedback Loop (CRITICAL):
The product lifecycle is circular, not linear. METRO's CFD-XXX entries from post-launch feedback become HORIZON's input for the next iteration cycle. This feedback loop is what transforms a launched product into an evolving product.
┌─────────────────────────────────────────────────────────────┐
│ PRODUCT LIFECYCLE │
│ │
│ HORIZON ──► STUDIO ──► DEVLAB ──► METRO ──► HORIZON │
│ v0.1 v0.4 v0.7 v0.9 v0.1+ │
│ │ │ ▲ │
│ │ │ │ │
│ └──────────── CFD-XXX ─────────┴──────────┘ │
│ (feedback loop) │
└─────────────────────────────────────────────────────────────┘
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.
- 4d ago First seen · 155 lines · 46 tokens per session scan A dc0982f7cafc
metro is an agent published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 1,303 once invoked, about $0.0002 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
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
model-compatibility
Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
design-rules
Condensed 10 Golden Rules from the Agent Design Bible.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…