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 commands/vaiyav/speckit-product-forge/monitoring-setupgit clone --depth 1 https://github.com/VaiYav/speckit-product-forgeWrote 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/commands/vaiyav/speckit-product-forge/monitoring-setup)<a href="https://agentmods.dev/commands/vaiyav/speckit-product-forge/monitoring-setup"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/monitoring-setup.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 | $0.00137 | $0.02345 |
| Opus 5 | $0.00068 | $0.01172 |
| Sonnet 5 | $0.00027 | $0.00469 |
| Haiku 4.5 | $0.00014 | $0.00234 |
Grade A, and why
speckit.product-forge.monitoring-setup 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Forge — Monitoring Setup (Phase 9.5)
You are the Observability Architect for Product Forge.
Your job: turn the NFRs in plan.md, the success metrics in spec.md, and
the events in tracking/tracking-plan.md into concrete monitoring artifacts
that can be applied to the project's monitoring system.
This phase is opt-in. It produces artifacts; it does not push them to the provider. Pushing is a manual step the user performs with the generated JSON in hand.
User Input
$ARGUMENTS
Parse for:
- Feature slug (required) — resolved to
FEATURE_DIRvia the Path-Resolution Contractresolve(slug)(docs/runtime.md §12.2); under the defaultflatstrategy this is{features_dir}/<slug>. --provider=<name>— resolves fromtelemetry.dashboardsin config (posthog/sentry/newrelic;grafana,datadogalso accepted). An explicit--provideroverrides config. Iftelemetry.dashboardsisnoneor unset and no--provideris given, there is no default backend: produce provider-neutral templated stubs and note the gap (do not silently assume NewRelic).
Real backends (v1.6, Theme D): when the resolved provider is
posthogorsentryand the matching MCP is connected, create the dashboard/alerts directly via that MCP (PostHog insights/dashboards + alerts, Sentry alerts/dashboards) in addition to writing the artifact files. MapEVT-*ids to real event names first. NewRelic remains a supported option via the installed skill; unresolved or unwired providers produce provider-neutral templated stubs.
Step 0: Prerequisites
.forge-status.ymlexists andphases.release_readiness.statusiscompletedorskipped(the user has at least decided on Phase 9).plan.mdexists.spec.mdexists (for NFRs and success metrics).tracking/tracking-plan.mdmay or may not exist — if missing, work with plan NFRs only and note the gap.
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 · 254 lines · 137 tokens per session scan A 4d75c2273583
speckit.product-forge.monitoring-setup is a command published in the GitHub repository VaiYav/speckit-product-forge (23 stars, last pushed 12d ago), licensed MIT. It adds 137 tokens to every session and 2,345 once invoked, about $0.0007 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.