Borrowing it
Nothing to install: this file belongs to jmanhype/speckit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jmanhype/speckit/main/.claude/commands/speckit-workflow-v2.mdgit clone --depth 1 https://github.com/jmanhype/speckitWrote 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/jmanhype/speckit/speckit-workflow-v2)<a href="https://agentmods.dev/commands/jmanhype/speckit/speckit-workflow-v2"><img src="https://agentmods.dev/badge/commands/jmanhype/speckit/speckit-workflow-v2/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/jmanhype/speckit/speckit-workflow-v2"><img src="https://agentmods.dev/badge/commands/jmanhype/speckit/speckit-workflow-v2.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 | $0.00066 | $0.01487 |
| Opus 5.5 | $0.00026 | $0.00595 |
| Sonnet 5.5 | $0.00013 | $0.00297 |
| Haiku 4.5 | $0.00007 | $0.00149 |
Grade A, and why
speckit-workflow-v2 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Speckit Workflow v2 (Feature-complete)
Objective
Convert "$ARGUMENTS" into a validated spec-driven change using every relevant Spec Kit phase: constitution → specify → (clarify) → plan → contract → checklist → tasks → analyze → implement.
Prechecks
- If /speckit.* commands aren't visible in /help: !uv tool install specify-cli --from git+https://github.com/github/spec-kit.git !specify init --here --ai claude !specify check
Inputs
$ARGUMENTS= brief + optional flags:--domains "<csv>"e.g., "security,privacy,accessibility,performance,observability"--strictfail the run if checklist/analyze/contract gates don't pass--autoproceed without asking between gates (unless a blocking ambiguity is detected)--paralleluse specialized sub-agents for parallel backend/frontend implementation
Flow
1) Constitution (first run only)
- If no principles exist, run: /speckit.constitution Create principles for code quality, testing standards, UX consistency, performance/SLOs, security, accessibility.
2) Specify (WHAT/WHY)
- Run: /speckit.specify $ARGUMENTS
- Keep tech decisions out of the spec.
3) Clarify (targeted; only if needed)
- If the spec is underspecified, run: /speckit.clarify Ask only focused questions to resolve ambiguities blocking the plan.
4) Plan (HOW)
- Run: /speckit.plan Draft the technical plan aligned to the spec: architecture, data model, interfaces, testing/observability, performance budgets, risks.
- If API endpoints are defined, ensure OpenAPI spec is created in
specs/<feature>/contracts/openapi.yaml
5) Contract Validation (API gate) - NEW
- If
specs/<feature>/contracts/openapi.yamlexists:- Use
openapi-spec-authoragent or run directly:specmatic backward-compatibility-check --target-path ./specs/<feature>/contracts/openapi.yaml - Rules:
- Adding optional fields: ✅ ALLOWED
- Adding new endpoints: ✅ ALLOWED
- Removing endpoints/fields: ❌ BREAKING
- Changing field types: ❌ BREAKING
- If
--strictand breaking changes detected → stop with actionable summary - For WIP APIs, add
tags: ["WIP"]to bypass breaking change failures
- Use
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.
- 1mo ago First seen · 136 lines · 66 tokens per session scan A 224c14725340
speckit-workflow-v2 is a command published in the GitHub repository jmanhype/speckit (26 stars, last pushed 7mo ago), licensed MIT. It adds 66 tokens to every session and 1,487 once invoked, about $0.0003 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 2026-09-01.
Other commands, from other repositories
paul:plan-fix
Plan fixes for UAT issues from verify.
lavra-qa
Browser-based QA verification of the running app -- systematic testing from the user's perspective.
test-browser
Run browser tests on pages affected by current PR or branch.
implement
Execute all implementation tasks from tasks.md with test-driven development, parallel batching, and atomic commits.
tasks
Generate TDD task breakdown from plan.md with test-first sequencing and mockup-first mode (--ui-first).
paul:verify
Guide manual user acceptance testing of recently built features.