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.
git 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/tracking-plan)<a href="https://agentmods.dev/commands/vaiyav/speckit-product-forge/tracking-plan"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/tracking-plan.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 | $0.00076 | $0.02990 |
| Opus 5 | $0.00038 | $0.01495 |
| Sonnet 5 | $0.00015 | $0.00598 |
| Haiku 4.5 | $0.00008 | $0.00299 |
Grade A, and why
speckit.product-forge.tracking-plan 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 8d 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 — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Forge — Analytics Tracking Plan
You are the Analytics Architect for Product Forge. Your goal: generate a complete, implementation-ready tracking plan from the feature's user journeys and success metrics — so analytics is wired correctly from day one.
User Input
$ARGUMENTS
Step 1: Validate Prerequisites
- Read
.forge-status.yml—product_specmust becompleted(Phase 2 done) - Read
product-spec/product-spec.md→ success metrics, user stories - Read
product-spec/journeys/journeys.yml→ all journeys (JRN/STEP/EDGE) and decision points; give each event a stableEVT-*id and map it to journey steps - Read
research/metrics-roi.md(if exists) → predicted KPIs
If not ready:
⚠️ Product spec (Phase 2) must be completed before generating a tracking plan. Run:
/speckit.product-forge.product-spec
Step 2: Detect Analytics Stack
Scan the codebase to identify the analytics SDK in use:
🔍 Detecting analytics stack...
Look for:
- Mixpanel:
mixpanel-browser,mixpanel.track(,import Mixpanel - Amplitude:
@amplitude/analytics-browser,amplitude.track( - Segment:
@segment/analytics-next,analytics.track( - PostHog:
posthog-js,posthog.capture( - Firebase Analytics:
firebase/analytics,logEvent( - Custom / none: no SDK found
Ask the user to confirm:
Analytics SDK detected: {SDK name or "None found"}
1. Is this correct, or are you using a different SDK?
(e.g., Mixpanel, Amplitude, Segment, PostHog, Firebase, Heap, custom)
2. Where should tracking calls be placed?
- [ ] Frontend only (Vue/React/mobile)
- [ ] Backend only (server-side events)
- [ ] Both (frontend + backend)
3. Do you have an existing event naming convention?
(e.g., "object_action", "OBJECT_ACTION", "Object Action")
If yes, paste an example event name.
Store: ANALYTICS_SDK, TRACKING_LAYER, NAMING_CONVENTION.
Step 3: Extract Events from User Journeys
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.
- 8d ago First seen · 392 lines · 76 tokens per session scan A bda48bd4e251
speckit.product-forge.tracking-plan is a command published in the GitHub repository VaiYav/speckit-product-forge (23 stars, last pushed 14d ago), licensed MIT. It adds 76 tokens to every session and 2,990 once invoked, about $0.0004 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.