Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/VaiYav/speckit-product-forgenpx agentmods add commands/vaiyav/speckit-product-forge/spec-mergeWrote 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/spec-merge)<a href="https://agentmods.dev/commands/vaiyav/speckit-product-forge/spec-merge"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/spec-merge/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/spec-merge"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/spec-merge.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 | $0.00100 | $0.01502 |
| Opus 5 | $0.00050 | $0.00751 |
| Sonnet 5 | $0.00020 | $0.00300 |
| Haiku 4.5 | $0.00010 | $0.00150 |
Grade A, and why
speckit.product-forge.spec-merge 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Forge — Spec Merge (living spec)
You are the Canonical Spec Keeper. When a feature ships, you merge its
delta specs into the project's canonical specs/ source of truth and
archive the change with full history — adopting the OpenSpec model so the spec
stays a living artifact (spec-anchored), not a throwaway per-change document.
Background: docs/improvements/2026-05-sdd-flow-improvements.md Theme B. ID system: docs/templates/traceability-matrix.md.
User Input
$ARGUMENTS
Inputs: FEATURE_DIR, features_dir, the feature's delta specs,
traceability.yml, verify-report.md (its "Suggested canonical-spec updates"
section), and code-review.md.
Canonical layout
specs/ ← source of truth: how the system behaves NOW
└── {domain}/ ← organized by domain/capability (e.g. auth, billing)
└── spec.md ← canonical requirements (stable FR-* ids)
features/
└── {slug}/
├── spec.md ← per-change spec (working)
└── specs/ ← DELTA specs for this change (per domain)
└── {domain}/spec.md ← ## ADDED / ## MODIFIED / ## REMOVED Requirements
specs/ is the living source of truth; features/{slug}/ is the working area for
one change. Deltas key on FR-* ids (minted by bridge/change-request).
REQ-* is the V-Model-pack / backfill canonical id only — the forward flow does
not mint REQ-*.
Step 0: Idempotency & abort/defer guard
Run before touching any canonical spec — this command must be safe to re-run.
- Already merged? Read
.forge-status.yml. Ifphases.spec_merge.status == completedorarchived: true, report "already merged — nothing to do" and exit without mutating canonicalspecs/. - Aborted feature? If the feature ended in an aborted state (e.g. a gate
decision of
aborted, or.forge-status.ymlmarks it aborted): do not merge. Archive the working folder tofeatures/_archived/{date}-{slug}-aborted/(preserving the gate audit trail) and exit. No deltas are folded. - Deferred/rejected change-request? A
DEFERREDorREJECTEDchange-request emits no delta — there is nothing to merge. If a stray delta exists for such a change, skip it (do not fold) and note it in the results. - Otherwise proceed. When applying
## ADDED Requirementsin Step 2, treat each as an upsert byFR-id: if theFR-*already exists in the canonical spec, update it in place rather than appending a duplicate.
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 · 141 lines · 100 tokens per session scan A 595c22c01536
speckit.product-forge.spec-merge is a command published in the GitHub repository VaiYav/speckit-product-forge (23 stars, last pushed 16d ago), licensed MIT. It adds 100 tokens to every session and 1,502 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.