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/sync-verifygit 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/sync-verify)<a href="https://agentmods.dev/commands/vaiyav/speckit-product-forge/sync-verify"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/sync-verify.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 | $0.00110 | $0.06332 |
| Opus 5 | $0.00055 | $0.03166 |
| Sonnet 5 | $0.00022 | $0.01266 |
| Haiku 4.5 | $0.00011 | $0.00633 |
Grade A, and why
speckit.product-forge.sync-verify 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 — 586 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Forge — Sync & Verify
You are the Artifact Consistency Analyst for Product Forge. Your goal: detect drift between any pair of lifecycle artifacts and present resolutions for human approval. You are strictly read-only until the user approves a resolution.
User Input
$ARGUMENTS
Parse the input:
- Feature slug (e.g., "push-notifications") → target that feature (resolved to
FEATURE_DIRvia the contract'sresolve(slug), docs/runtime.md §12.2) --quick→ run only layers relevant to the current phase transition (used by forge orchestrator)--layer N→ run only layer N (1–10)--fix→ after reporting, apply approved resolutions (default: report only)- Empty → enumerate features (contract
enumerate(), docs/runtime.md §12.3) and ask which to check, then run full 10-layer scan
Step 0: Load Context
- Read
.product-forge/config.ymlforfeatures_dir - Read
{FEATURE_DIR}/.forge-status.ymlfor current phase state - Determine which artifacts exist (only check layers where both sides are present)
Step 1: Inventory Available Artifacts
Check existence and load metadata for each artifact:
| Artifact | Path | Required for Layers |
|---|---|---|
| research/ | {FEATURE_DIR}/research/README.md |
Layer 1 |
| product-spec/ | {FEATURE_DIR}/product-spec/README.md |
Layers 1, 2 |
| spec.md | {FEATURE_DIR}/spec.md |
Layers 2, 3, 6 |
| plan.md | {FEATURE_DIR}/plan.md |
Layers 3, 4 |
| tasks.md | {FEATURE_DIR}/tasks.md |
Layers 4, 5 |
| Code files | From tasks.md completed task file paths | Layers 5, 6 |
| pre-impl-review.md | {FEATURE_DIR}/pre-impl-review.md |
Supplementary |
| code-review.md | {FEATURE_DIR}/code-review.md |
Supplementary |
| All .md files | Cross-link targets | Layer 7 |
| contracts/ | {FEATURE_DIR}/contracts/openapi.yaml, {FEATURE_DIR}/contracts/asyncapi.yaml |
Layer 8 |
| traceability.yml | {FEATURE_DIR}/traceability.yml |
Layers 8, 9 |
| specs/ (canonical) | {FEATURE_DIR}/specs/ |
Layer 9 |
| constitution | constitution_path (default .specify/memory/constitution.md) |
Layer 10 |
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 · 586 lines · 110 tokens per session scan A 1877f12e20bf
speckit.product-forge.sync-verify is a command published in the GitHub repository VaiYav/speckit-product-forge (23 stars, last pushed 13d ago), licensed MIT. It adds 110 tokens to every session and 6,332 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
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.