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-implement)<a href="https://agentmods.dev/commands/alonf/specrew/speckit.specrew-speckit.before-implement"><img src="https://agentmods.dev/badge/commands/alonf/specrew/speckit.specrew-speckit.before-implement.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 | $0.00005 | $0.01073 |
| Opus 5 | $0.00003 | $0.00536 |
| Sonnet 5 | $0.00001 | $0.00215 |
| Haiku 4.5 | $0.00001 | $0.00107 |
Grade A, and why
speckit.specrew-speckit.before-implement 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 3d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate Execution Readiness
Before implementation starts, confirm the active iteration artifacts are approved and execution-ready.
Required checks
- Confirm the latest iteration plan has an approval verdict and is still the active source of truth.
- Verify execution is not bypassing unresolved review findings or missing phase artifacts.
- Run
pwsh -File .specify/extensions/specrew-speckit/scripts/validate-governance.ps1 -ProjectPath .when iteration artifacts are available. - When the active iteration includes Phase 2 hardening-gate scope (
FR-031throughFR-033), confirmquality/hardening-gate.mdexists and records explicit review of:- security surface analysis
- error-handling expectations
- retry and idempotency requirements
- test-integrity targets
- For a Phase 2 hardening slice, confirm the hardening gate status is implementation-ready:
- explicit sign-off is recorded, or
- each unresolved critical concern has explicit human developer deferral approval recorded
- Do not treat
TBD, omitted rationale, or agent-only deferral decisions as implementation-ready for critical security, resilience, or operational concerns. - Keep later quality behavior truthful. Do not claim dedicated bug-hunter execution, strongest-class routing enforcement, known-traps workflows, or quality-drift automation are already active unless the current slice actually delivered them.
Lifecycle-adjacent command: /speckit.analyze (before-implement)
Surface /speckit.analyze at this before-implement boundary, but only after /speckit.tasks has produced a complete tasks.md. It requires the full artifact set — spec.md, plan.md, and tasks.md — and performs an additive cross-artifact consistency and quality review across them.
- It is additive to Specrew governance validation: it complements the governance checks and does not replace them.
- It is only meaningful once a complete
tasks.mdexists; there is nothing for it to analyze before tasks are generated. - If you reach
/speckit.analyzebefore a completetasks.mdexists, do not run it prematurely — return at the before-implement boundary after/speckit.taskscompletes.
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.
- 3d ago First seen · 76 lines · 5 tokens per session scan A f710d0587855
speckit.specrew-speckit.before-implement is a command published in the GitHub repository alonf/specrew (54 stars, last pushed 5d ago), licensed MIT. It adds 5 tokens to every session and 1,073 once invoked, about $0.0000 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 2026-09-03.
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.