Borrowing it
Nothing to install: this file belongs to joestump/claude-plugin-sdd. 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/joestump/claude-plugin-sdd/main/CLAUDE.mdgit clone --depth 1 https://github.com/joestump/claude-plugin-sddWrote 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/joestump/claude-plugin-sdd/claude-md)<a href="https://agentmods.dev/instructions/joestump/claude-plugin-sdd/claude-md"><img src="https://agentmods.dev/badge/instructions/joestump/claude-plugin-sdd/claude-md/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/instructions/joestump/claude-plugin-sdd/claude-md"><img src="https://agentmods.dev/badge/instructions/joestump/claude-plugin-sdd/claude-md.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 | $0.01580 | $0.01580 |
| Opus 5.5 | $0.00632 | $0.00632 |
| Sonnet 5.5 | $0.00316 | $0.00316 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
claude-plugin-sdd 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 16d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Context
This project uses the SDD plugin for architecture governance.
- Architecture Decision Records are in
docs/adrs/ - Product Requirements Documents are in
docs/prds/ - Specifications are in
docs/openspec/specs/
SDD Skills
| Skill | Purpose |
|---|---|
/sdd:prd |
Create a Product Requirements Document for a client-facing capability |
/sdd:adr |
Create a new Architecture Decision Record |
/sdd:spec |
Create a new specification |
/sdd:list |
List all ADRs and specs with status |
/sdd:status |
Update the status of an ADR or spec |
/sdd:docs |
Generate a documentation site |
/sdd:init |
Set up CLAUDE.md with architecture context |
/sdd:prime |
Load architecture context into session |
/sdd:check |
Quick-check code against ADRs and specs for drift |
/sdd:audit |
Comprehensive design artifact alignment audit |
/sdd:discover |
Discover implicit architecture from existing code |
/sdd:plan |
Break a spec into trackable issues with project grouping and branch conventions |
/sdd:organize |
Retroactively group issues into tracker-native projects |
/sdd:enrich |
Add branch naming and PR conventions to existing issues |
/sdd:triage |
Give each open issue a verdict, close only on evidence from main, and apply exactly one size/* label |
/sdd:work |
Pick up tracker issues and implement them in parallel using git worktrees |
/sdd:review |
Review and merge PRs using reviewer-responder agent pairs |
/sdd:respond |
Address review feedback on a PR: make the code fixes, push, and reply to each thread |
/sdd:graph |
Build and query the artifact graph (validate, impact, ancestors, chain, orphans, cycles, backfill) |
/sdd:index |
Index ADRs, specs, and code into qmd collections for hybrid semantic search |
/sdd:report-friction |
File a feedback issue against the SDD plugin when one of its skills caused significant churn |
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.
- 16d ago Changed · +15 tokens per session 9749daad755a
- 1mo ago Changed · +1 lines · +34 tokens per session fe62ae32f2ed
- 1mo ago Changed · +3 lines · +85 tokens per session 87151f255d29
- 2mo ago Changed · +2 lines · +133 tokens per session a6807590e966
- 2mo ago First seen · 90 lines · 1,313 tokens per session scan A 4dbb1de459e1
claude-plugin-sdd CLAUDE.md is an instructions file published in the GitHub repository joestump/claude-plugin-sdd (35 stars, last pushed 6d ago), licensed MIT. It adds 1,580 tokens to every session, about $0.0063 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 2026-08-30.
claude-plugin-sdd CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| claude-plugin-sdd CLAUDE.mdjoestump/claude-plugin-sdd | Instructions file | 35 | 6d ago | MIT | A | 1,580 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 3d ago | MIT | A | 4,313 | Codex, OpenCode |