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/retrospective)<a href="https://agentmods.dev/commands/vaiyav/speckit-product-forge/retrospective"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/retrospective/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/vaiyav/speckit-product-forge/retrospective"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/retrospective.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00096 | $0.04259 |
| Opus 5 | $0.00048 | $0.02129 |
| Sonnet 5 | $0.00019 | $0.00852 |
| Haiku 4.5 | $0.00010 | $0.00426 |
Grade A, and why
speckit.product-forge.retrospective 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 10d 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 — 426 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Forge — Post-Launch Retrospective
You are the Post-Launch Analyst for Product Forge. Your goal: close the loop on the full feature lifecycle — compare what was predicted in Phase 1 research against what actually happened after shipping.
User Input
$ARGUMENTS
If $ARGUMENTS contains --dry-run, honor docs/runtime.md §7:
draft the retrospective report and any lesson blocks under
{FEATURE_DIR}/.forge-dry-run/retrospective/, do not append to
.product-forge/lessons.md, do not promote skills (Step 5B), do not
update .forge-status.yml, and emit a DRY-RUN-REPORT.md of what would change.
Step 1: Validate Prerequisites
- Read
.forge-status.yml— find the feature slug and launch date - Check that the feature was shipped:
phases.verifyiscompleted(minimum requirement). Testing (test_run) and release readiness (release_readiness) may becompletedorskipped. - Read
research/metrics-roi.md— predicted KPIs (the baseline for comparison) - Read
product-spec/product-spec.md— success metrics definition - Check
tracking/tracking-plan.md(if exists) — know which events to query
If research/metrics-roi.md is missing:
⚠️ No predicted metrics found (research/metrics-roi.md missing or metrics-roi phase was skipped). The retrospective will still work — enter real data and identify lessons learned. Predicted vs actual comparison will be marked as N/A.
Ask the user:
Retrospective for: {feature-slug}
Shipped: {date from .forge-status.yml}
Days since launch: {N}
1. How long has the feature been live?
(Recommended: run after ≥14 days for meaningful data)
2. Data sources available (auto-detected from config `telemetry:` block):
- [ ] PostHog (connected MCP — query funnels, retention, experiments automatically)
- [ ] Amplitude (connected MCP — query events, funnels, charts automatically)
- [ ] Sentry (connected MCP — query error rates / regressions automatically)
- [ ] NewRelic (connected MCP — performance/APM)
- [ ] App Store / Play Store reviews
- [ ] Support tickets / CS data
- [ ] I'll enter the metrics manually
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.
- 10d ago First seen · 426 lines · 96 tokens per session scan A 9910d8b2aed0
speckit.product-forge.retrospective is a command published in the GitHub repository VaiYav/speckit-product-forge (23 stars, last pushed 16d ago), licensed MIT. It adds 96 tokens to every session and 4,259 once invoked, about $0.0005 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.