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.
npx skills add viamus/claude-sdd-plugin --skill sdd-reviewgit clone --depth 1 https://github.com/viamus/claude-sdd-pluginWrote 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/skills/viamus/claude-sdd-plugin/sdd-review)<a href="https://agentmods.dev/skills/viamus/claude-sdd-plugin/sdd-review"><img src="https://agentmods.dev/badge/skills/viamus/claude-sdd-plugin/sdd-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/skills/viamus/claude-sdd-plugin/sdd-review"><img src="https://agentmods.dev/badge/skills/viamus/claude-sdd-plugin/sdd-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 | $0.00030 | $0.00859 |
| Opus 5 | $0.00015 | $0.00430 |
| Sonnet 5 | $0.00006 | $0.00172 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
sdd-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 9d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDD Review — Validate Specification
You are the SDD Orchestrator reviewing a specification for completeness and quality.
Instructions
-
Determine which spec to review:
- If
$ARGUMENTSis provided, use it as the path - Otherwise, search
specs/for files withstatus: draftorstatus: reviewin frontmatter - If multiple found, list them and ask the user which to review
- If none found, say: "No pending specs found. Use /sdd:sdd-init to create a new one."
- If
-
Read the spec file completely
-
Validate each mandatory section with these criteria:
Validation Checklist
| # | Section | Criterion | Weight |
|---|---|---|---|
| 1 | Frontmatter | Has name, status, created_at |
Required |
| 2 | Overview | Non-empty, at least 1 sentence describing purpose | Required |
| 3 | Inputs | At least 1 input with Name, Type, and Constraints defined | Required |
| 4 | Outputs | At least 1 output with Name, Type, and Description defined | Required |
| 5 | Business Rules | At least 1 numbered rule, each rule is actionable (not vague) | Required |
| 6 | Error Handling | At least 1 error scenario with Scenario, Type/Code, and Message | Required |
| 7 | Dependencies | Section exists (may be empty if no deps) | Required |
- Generate a validation report:
## 📋 SDD Review Report: {spec-name}
| # | Section | Status | Notes |
|---|---------|--------|-------|
| 1 | Frontmatter | ✅/❌ | ... |
| 2 | Overview | ✅/❌ | ... |
| 3 | Inputs | ✅/❌ | ... |
| 4 | Outputs | ✅/❌ | ... |
| 5 | Business Rules | ✅/❌ | ... |
| 6 | Error Handling | ✅/❌ | ... |
| 7 | Dependencies | ✅/❌ | ... |
**Result: X/7 criteria met**
-
If ALL pass (7/7):
- Update the spec frontmatter: set
status: approvedandupdated_atto today - Say: "✅ Spec approved! Run /sdd:sdd-gen to generate the code."
- Update the spec frontmatter: set
-
If ANY fail:
- Do NOT change the status
- For each failed criterion, provide a specific suggestion of what to add
- Say: "❌ Spec needs adjustments. Fix the items above and run /sdd:sdd-review again."
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.
- 9d ago First seen · 84 lines · 30 tokens per session scan A 40d972de88fa
sdd-review is a skill published in the GitHub repository viamus/claude-sdd-plugin (4 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 859 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
setup
A setup and prerequisite check for the Reqord plugin. It checks required command-line tools, GitHub sign-in, and whether a project has been initialized.
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…
context
A shared reference for Reqord's data model and command-line rules. Reqord uses records such as requirements, specifications, project context, and feedback to organise requirements-driven development.
feedback
A feedback-management skill from the Reqord project, including commands for handling feedback and checking the repository.
brief
A Reqord workflow for preparing a brief from project scope and context. Reqord is a requirements-management tool, and the workflow includes argument handling and a detailed specification mode.
status
A Reqord progress dashboard for requirements and specifications. It groups work by status and lists design-document readiness and unresolved feedback.