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/alonf/specrewWrote 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/alonf/specrew/speckit.specrew-speckit.before-specify)<a href="https://agentmods.dev/commands/alonf/specrew/speckit.specrew-speckit.before-specify"><img src="https://agentmods.dev/badge/commands/alonf/specrew/speckit.specrew-speckit.before-specify/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/alonf/specrew/speckit.specrew-speckit.before-specify"><img src="https://agentmods.dev/badge/commands/alonf/specrew/speckit.specrew-speckit.before-specify.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 | $0.00014 | $0.00372 |
| Opus 5.5 | $0.00006 | $0.00149 |
| Sonnet 5.5 | $0.00003 | $0.00074 |
| Haiku 4.5 | $0.00001 | $0.00037 |
Grade A, and why
speckit.specrew-speckit.before-specify 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 2mo 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.
What it actually says
Run the Specrew Design Workshop Before Specifying
You are producing a feature specification on a Specrew-governed project. Specrew does NOT generate the spec from informed defaults — the spec must be lens-informed, produced WITH the human through the design workshop. Before you write any spec content, do this:
Required
- Invoke the
specrew-design-workshopskill and work the applicable design lenses WITH the human — product-domain first, then architecture-core, component-design, data-storage, integration-api, observability-resilience, devops-operations, requirements-nfr, ui-ux, and code-implementation as applicable. Work one lens at a time: present each lens, get the human's decide / delegate / skip, and record the confirmation. Never fabricate a lens agreement — the SC-026 provenance gate validates that each lens record reflects a real human answer. - Only after the workshop is complete and the lens records exist do you write
spec.md, informed by the confirmed lens decisions (lens-informed, not lens-decorated). - Then stop at the specify boundary and render the human re-entry packet for the verdict. Do not free-run into clarify.
Failure behavior
If you are about to generate the spec from informed defaults without having run the workshop with the human, STOP — that is raw Spec Kit behavior, and this project is Specrew-governed. The specrew-design-workshop skill is the Specrew specify entry; the speckit.specify generation is the spec-writer that runs only after the workshop. Invoke the workshop and work the lenses with the human first.
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.
- 2mo ago First seen · 18 lines · 14 tokens per session scan A e4115a26f804
speckit.specrew-speckit.before-specify is a command published in the GitHub repository alonf/specrew (54 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 372 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
speckit.specrew-speckit.before-specify compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| speckit.specrew-speckit.before-specifyalonf/specrew | Command | 54 | yesterday | MIT | A | 14 | Claude Code |
| profilecathrynlavery/diagram-design | Command | 65k | 3d ago | MIT | A | 16 | Claude Code |
| erne-animateJubaKitiashvili/everything-react-native-expo | Command | 50 | 29d ago | MIT | A | 21 | Claude Code |
| ui-flow-reviewMRCalderon3D/everything-game-dev-code | Command | 104 | 28d ago | MIT | A | 15 | Claude Code |
| responsive-design-specialistimsaif/design-with-claude | Command | 11 | yesterday | MIT | A | 36 | Claude Code |
| design-auditw2ur/claude-code-setup | Command | 2 | 3d ago | MIT | A | 30 | Claude Code |
| ppt-image2-editable-rebuildwwe-dog/ppt-image2-editable-rebuild | Command | 204 | 5mo ago | Unlicense | A | 15 | Claude Code |