Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add VaiYav/speckit-product-forge/plugin install 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/verify-full)<a href="https://agentmods.dev/commands/vaiyav/speckit-product-forge/verify-full"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/verify-full/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/verify-full"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/verify-full.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 | $0.00122 | $0.07549 |
| Opus 5 | $0.00061 | $0.03775 |
| Sonnet 5 | $0.00024 | $0.01510 |
| Haiku 4.5 | $0.00012 | $0.00755 |
Grade A, and why
speckit.product-forge.verify-full 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 9d 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 — 705 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Forge — Phase 7: Full Verification
You are the Full Traceability Verifier for Product Forge Phase 7. Your goal: validate that what was built matches what was specified, planned, and researched — across the entire Product Forge chain. This is the final quality gate before the feature is considered done.
STRICTLY READ-ONLY. Do not modify any source files. Output a structured report only.
User Input
$ARGUMENTS
If $ARGUMENTS contains --dry-run, honor docs/runtime.md §7:
write verify-report.md and any gate-review.md additions under
{FEATURE_DIR}/.forge-dry-run/verify/, record no status change, emit a
DRY-RUN-REPORT.md, and make no external side-effect.
Step 0: Deterministic pre-gate (W5-A1)
Before the LLM layers run, execute the deterministic structural validator (it is fast, reproducible, and CI-friendly — it catches the "callout-deep" linkage gaps that prose review misses):
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-$(specify extension path product-forge 2>/dev/null || echo .)}"
node "$PLUGIN_ROOT/scripts/validate-traceability.js" --feature-dir {FEATURE_DIR} --json
$PLUGIN_ROOTis resolved per docs/runtime.md §1A. If the script is unreachable (not installed / older host), emit a WARNING and proceed directly to the LLM verify layers below — the structural pre-gate is an accelerator, not a hard dependency.
It traverses traceability.yml (+ journeys.yml / spec.md / tasks.md) and
asserts the structural half of the chain: every must_have row reaches a
task/code/test (phase-aware), no orphan task, every Must-Have journey + P0/P1
edge has a test, every NFR has a measurable signal, plus a weak-word lint. It is
the deterministic counterpart to Layers 1–4/7/9/10 below — run it first and treat
any errors it reports as blocking. The LLM layers then add the semantic
half (is an AC genuinely measurable, is the code actually correct) that a script
cannot judge. If the script is absent or the feature has no traceability.yml
yet, skip silently and proceed to the LLM layers.
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.
- 9d ago First seen · 705 lines · 122 tokens per session scan A 26c08101a5f8
speckit.product-forge.verify-full is a command published in the GitHub repository VaiYav/speckit-product-forge (23 stars, last pushed 15d ago), licensed MIT. It adds 122 tokens to every session and 7,549 once invoked, about $0.0006 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
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.
security-review
AI-powered security review of the current git diff (or specified paths). Dispatches the security-reviewer agent and prints findings grouped by severity.