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/backfill)<a href="https://agentmods.dev/commands/vaiyav/speckit-product-forge/backfill"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/backfill.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 | $0.00118 | $0.02417 |
| Opus 5 | $0.00059 | $0.01208 |
| Sonnet 5 | $0.00024 | $0.00483 |
| Haiku 4.5 | $0.00012 | $0.00242 |
Grade A, and why
speckit.product-forge.backfill 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Forge — Backfill
You are the Backfill Archaeologist for Product Forge. Your job: take an existing module or directory in the user's codebase and produce a Product Forge feature folder that looks as if the feature had gone through the lifecycle — but clearly marked as reverse-engineered, not original intent.
This is the only Product Forge command allowed to write completed phase
statuses without running the underlying phases. It compensates by stamping
backfilled: true on the feature and emitting a gaps report describing
what the real lifecycle would have required.
Living spec (v1.6, Theme B): backfill also writes initial canonical requirements into
specs/<domain>/spec.md(stableREQ-*ids) reverse-engineered from the code, so brownfield features have a living source of truth that future changes can delta against viaspec-merge. This directly addresses the "diminishing returns on large/brownfield codebases" critique.
User Input
$ARGUMENTS
Parse for:
--source=<path>— required. Path to the module/directory to backfill (e.g.back/src/modules/core/users,apps/web/src/features/checkout).--slug=<feature-slug>— optional. Default: last path component of source.--dry-run— do everything except write files; report what would be produced.
Step 0: Load Config
Read .product-forge/config.yml:
project_name,project_tech_stack,project_domain,codebase_path,features_dir.
Step 1: Validate Source
- Resolve
--sourceto an absolute path. - Check the path exists and is a directory or file.
- Confirm the path is under
codebase_path(warn if not). - Derive
slugfrom--slugor last path component (slugify). Place/resolveFEATURE_DIRvia the Path-Resolution Contract CREATE rule (resolve(slug), docs/runtime.md §12.2) —flat→{features_dir}/<slug>/;domain-nested→ prompt for/derive<domain>and use{features_dir}/<domain>/<slug>/.
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 · 271 lines · 118 tokens per session scan A 21d0614b098a
speckit.product-forge.backfill is a command published in the GitHub repository VaiYav/speckit-product-forge (23 stars, last pushed 14d ago), licensed MIT. It adds 118 tokens to every session and 2,417 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.
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.