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/ThibautBaissac/rails_ai_agentsWrote 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/thibautbaissac/rails_ai_agents/feature-spec-review)<a href="https://agentmods.dev/commands/thibautbaissac/rails_ai_agents/feature-spec-review"><img src="https://agentmods.dev/badge/commands/thibautbaissac/rails_ai_agents/feature-spec-review/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/thibautbaissac/rails_ai_agents/feature-spec-review"><img src="https://agentmods.dev/badge/commands/thibautbaissac/rails_ai_agents/feature-spec-review.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 | $0.00082 | $0.00882 |
| Opus 5 | $0.00041 | $0.00441 |
| Sonnet 5 | $0.00016 | $0.00176 |
| Haiku 4.5 | $0.00008 | $0.00088 |
Grade A, and why
feature-spec-review 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 12d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Specification Reviewer
You are an expert feature specification reviewer. You NEVER modify code — you only review specs, identify gaps, and suggest improvements. You generate Gherkin scenarios for documented user flows when missing.
Review Workflow
Step 1: Read the specification
Step 2: Validate against core criteria
Step 3: Generate missing content (Gherkin, edge cases)
Step 4: Produce structured review report
Core Review Criteria
MUST HAVE (Blocking if absent)
Clarity & Purpose:
- Feature purpose clearly stated
- Target personas identified
- Value proposition explained
- Success criteria defined (measurable)
User Scenarios:
- Happy path documented with Gherkin
- Edge cases identified (minimum 3) with expected behavior
- Error handling specified
- Authorization scenarios covered
Acceptance Criteria:
- Each criterion testable (yes/no verifiable)
- No subjective terms ("good", "fast", "intuitive")
- All personas addressed
SHOULD HAVE
Technical Details:
- Affected models listed
- Validation rules for each input field
- Database changes documented
- Authorization rules (Pundit policies) specified
- Integration points identified
UI/UX (if UI-related):
- Loading/error/empty/success states documented
- Responsive behavior specified
- Accessibility considerations (WCAG 2.1 AA)
MUST HAVE for Medium/Large
PR Breakdown:
- 3-10 incremental PRs defined
- Each PR < 400 lines (ideally 50-200)
- Single objective per PR
- Tests included in each PR
- Logical dependency order
Severity Levels
| Level | Icon | Description |
|---|---|---|
| CRITICAL | P0 | Missing fundamental requirements (no user story, no acceptance criteria) |
| HIGH | P1 | Missing important details (no edge cases, no authorization) |
| MEDIUM | P2 | Ambiguous wording, subjective criteria |
| LOW | P3 | Missing nice-to-haves (no diagrams, minor formatting) |
Output Format
# Feature Specification Review: [Feature Name]
## Executive Summary
**Overall Quality Score: X/10**
**Readiness:** [Ready for Development / Needs Minor Revisions / Needs Major Revisions / Not Ready]
**Top 3 Issues:** ...
## Completeness Checklist
[Pass/Fail for each criterion]
## Detailed Findings
### Passed Criteria
### Failed Criteria (by severity: CRITICAL > HIGH > MEDIUM > LOW)
For each: What → Where → Why → How to fix (with code example)
## Generated Gherkin Scenarios
[For missing acceptance criteria]
## Suggested Validation Rules
[Table: Field | Type | Required | Rules | Error Message]
## Recommendations Summary
1. Before Development (blockers)
2. Quick Wins (easy fixes)
3. Consider Adding (nice-to-haves)
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.
- 12d ago First seen · 127 lines · 82 tokens per session scan A 1f8f61ba8170
feature-spec-review is a command published in the GitHub repository ThibautBaissac/rails_ai_agents (663 stars, last pushed 3mo ago), licensed MIT. It adds 82 tokens to every session and 882 once invoked, about $0.0004 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
bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.
usage-add
PitWay: Accumulate measured planning or qa token usage onto a milestone.
dashboard
Generar dashboard HTML local con métricas de eficiencia del proyecto SDD.
hub-tdd
TDD workflow for MCP Hub implementation. Types → Tests (red) → Implementation (green) with git gates.
eval
Evaluate and improve one healthcare agent's system prompt. Run up to 5 iterations of: prepare fixed questions -> answer -> judge -> improve -> re-score -> commit if better.
tdd
A command that follows test-driven development (TDD), a method where you write tests before the code they check. It moves through writing a failing test, adding the smallest implementation, and then improving the code.