Borrowing it
Nothing to install: this file belongs to yi-john-huang/sdd-mcp. 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/yi-john-huang/sdd-mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/yi-john-huang/sdd-mcpWrote 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/yi-john-huang/sdd-mcp/agents-md)<a href="https://agentmods.dev/instructions/yi-john-huang/sdd-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/yi-john-huang/sdd-mcp/agents-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/yi-john-huang/sdd-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/yi-john-huang/sdd-mcp/agents-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 | $0.00416 | $0.00416 |
| Opus 5 | $0.00208 | $0.00208 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
sdd-mcp AGENTS.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 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.
What it actually says
SDD-MCP Project Guidance
This repository develops sdd-mcp-server, a spec-driven workflow for Claude Code, Codex, and Oh My Pi (OMP).
Workflow
- Install the chosen host target, reload it, and accept the host's project trust prompt before starting.
- Small fixes: invoke
/skill:simple-task. - Formal work: invoke
/skill:sdd-requirements <feature-name>, then/skill:sdd-design,/skill:sdd-tasks, and/skill:sdd-implementafter each explicit approval. - Never cross an unapproved phase. When configured, test-case review is a separate explicit decision before tasks approval.
- Skills automatically restore durable status and approved compact context. Do not ask users to operate MCP tools or paste workflow JSON.
Repository layout
- Canonical components:
skills/,agents/,rules/,contexts/,hooks/,steering/,templates/. - Implementation:
src/; focused tests:src/__tests__/. - Specifications and project steering:
.spec/specs/and.spec/steering/. - Generated native targets are installed under
.claude/,.agents/+.codex/, or.omp/; do not hand-edit generated files.
Model routing
Planning, architecture, review, and security run inline on Sol/medium by default in OMP; project Sol/xhigh advisors are explicit opt-in. Claude uses current-turn Opus/Sonnet routing, while Codex may use one configured Sol/xhigh custom advisor.
Run implementation, TDD, simple tasks, and commits in the parent unless at least two genuinely independent implementation slices can run concurrently. If an advisor is explicitly invoked, allow one specialist without nesting; on model, auth, or agent failure, record one fallback and continue in the parent without retrying.
See docs/MODEL-ROUTING.md for route details and docs/WORKFLOW.md for the complete workflow.
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 · 27 lines · 416 tokens per session scan A 7952efe723be
sdd-mcp AGENTS.md is an instructions file published in the GitHub repository yi-john-huang/sdd-mcp (51 stars, last pushed 1mo ago), licensed MIT. It adds 416 tokens to every session, about $0.0021 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.