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 agentmods add instructions/viamus/claude-sdd-plugin/claude-mdgit 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/instructions/viamus/claude-sdd-plugin/claude-md)<a href="https://agentmods.dev/instructions/viamus/claude-sdd-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/viamus/claude-sdd-plugin/claude-md.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 | $0.00570 | $0.00570 |
| Opus 5 | $0.00285 | $0.00285 |
| Sonnet 5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
claude-sdd-plugin CLAUDE.md 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 5d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDD Orchestrator — Plugin Context
This project uses Spec-Driven Design (SDD). Code should only be generated after an approved specification.
Fundamental Rules
- Spec-First: Never generate implementation code without a corresponding approved spec in
specs/. Always ask: "Which approved spec am I following?" - Contract Fidelity: Generated code must implement EXACTLY what the spec defines — no more, no less. Do not add features, parameters, or behaviors that are not in the spec.
- Error Coverage: Every error scenario defined in the spec MUST have corresponding handling in the code.
- No Hallucination: If the spec does not define a behavior for a specific case, ask the developer instead of making it up.
Workflow
/sdd:sdd-init <name>— Creates a new spec from the template/sdd:sdd-learn <name> <sources>— Ingests docs, files, or web pages into spec context/sdd:sdd-build <name>— Builds the spec via guided conversation (auto-loads knowledge)/sdd:sdd-review— Validates whether the spec is complete/sdd:sdd-gen— Full pipeline: generate code + consistency check + quality audit + deliver/sdd:sdd-status— Shows the state of all specs and dependency graph
Pipeline (automated by sdd-gen)
Generate → Consistency Check → Quality Audit → Deliver
↑ auto-fix ↑ auto-fix
Check and audit are internal steps — the user only runs /sdd:sdd-gen.
Plugin Structure
claude-sdd-plugin/
├── .claude-plugin/
│ ├── plugin.json # Plugin manifest
│ └── marketplace.json # Marketplace catalog
├── skills/
│ ├── sdd-init/SKILL.md # Create spec
│ ├── sdd-learn/SKILL.md # Ingest knowledge for specs
│ ├── sdd-build/SKILL.md # Build spec via conversation
│ ├── sdd-review/SKILL.md # Validate spec
│ ├── sdd-gen/SKILL.md # Full pipeline
│ ├── sdd-check/SKILL.md # (internal) Consistency check
│ ├── sdd-audit/SKILL.md # (internal) Quality audit
│ └── sdd-status/SKILL.md # Status + dependency graph
├── templates/
│ └── spec-template.md
└── docs/
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.
- 5d ago First seen · 50 lines · 570 tokens per session scan A 3f6a2791b023
claude-sdd-plugin CLAUDE.md is an instructions file published in the GitHub repository viamus/claude-sdd-plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 570 tokens to every session, about $0.0029 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 instructions, from other repositories
platform-skills copilot-instructions.md
Copilot instructions for nitinjain999/platform-skills, covering platform engineering instructions for github copilot, version: 1.40.0, source: https://github.com/nitinjain999/platform-skills, response contract and core principles.
mcpforge AGENTS.md
AGENTS.md instructions for saagpatel/mcpforge, covering agents.md, what this project is, current state, stack and how to run.
sdd CLAUDE.md
Claude Code instructions for LiorCohen/sdd, covering claude.md, task management rules (mandatory), output rules, git rules and build rules.
aesth CLAUDE.md
Claude Code instructions for zircote-plugins/aesth, covering claude.md, architecture, key concepts, memory-first design and memory types.
auto-pilot CLAUDE.md
Claude Code instructions for IronRookieCoder/auto-pilot, covering 项目概况 and 同步更新规则.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).