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/zhu1090093659/spec_driven_develop/agents-mdgit clone --depth 1 https://github.com/zhu1090093659/spec_driven_developWhat 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 | $0.00513 | $0.00513 |
| Opus 5 | $0.00257 | $0.00257 |
| Sonnet 5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
spec_driven_develop 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 3d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Agent Instructions
Scope
These instructions apply to the whole repository.
Truth Sources
- Core workflow:
plugins/spec-driven-develop/skills/spec-driven-develop/SKILL.md - Shared workflow references:
plugins/spec-driven-develop/skills/spec-driven-develop/references/ - Claude Code sub-agent prompts:
plugins/spec-driven-develop/agents/ - OpenCode plugin entrypoint:
plugins/spec-driven-develop/opencode-plugin.js - Plugin manifests:
plugins/spec-driven-develop/.claude-plugin/plugin.json,plugins/spec-driven-develop/.codex-plugin/plugin.json, and the root.claude-plugin/marketplace.json - Validation and helper scripts:
scripts/ - User-facing docs:
README.mdandREADME.zh-CN.md - Persistent project memory: use the active coding agent's native project memory surface when available. Do not add a repository fallback memory file unless the workflow explicitly records that choice.
Development Rules
- Keep this repository Markdown-first. Do not add runtime dependencies unless a requested feature truly needs executable tooling.
- For workflow behavior changes, update the core
SKILL.md, the affected references/templates, and the affected agent prompts together. Avoid one-line prompt patches that leave other execution surfaces stale. - When changing user-visible behavior, keep
README.mdandREADME.zh-CN.mdconsistent. AGENTS.mdandCLAUDE.mdare active project-level instruction surfaces. Keep them aligned; useCLAUDE.mdonly for Claude Code-specific notes and point back here for shared rules.- New features or behavior changes must add or update relevant tests when an automated test surface exists. If no automated suite exists, run the closest static/syntax checks and document why no test was added.
- Record stable cross-session decisions in the native project memory surface when one is available. If none is available, record only agent-facing rules in
AGENTS.md/CLAUDE.md; do not invent a repo-local memory file without an explicit workflow decision.
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.
- 3d ago First seen · 35 lines · 513 tokens per session scan A cd24325fbc3b
spec_driven_develop AGENTS.md is an instructions file published in the GitHub repository zhu1090093659/spec_driven_develop (976 stars, last pushed 1mo ago), licensed MIT. It adds 513 tokens to every session, about $0.0026 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
spec-superflow AGENTS.md
Instructions for MageByte-Zero/spec-superflow, covering agents.md, what this is, commands, build typescript and run integration tests.
spec-superflow GEMINI.md
Instructions for MageByte-Zero/spec-superflow, covering spec-superflow and spec-superflow v1.0.1 | 阶段: {{state}} | 工作流: {{workflow}}.
spec-superflow copilot-instructions.md
Instructions for MageByte-Zero/spec-superflow, covering phase guard, ✅ 允许操作, ⛔ 禁止操作 and 🔔 决策点.
blueprint AGENTS.md
Instructions for owainlewis/blueprint, covering blueprint repository policy, principles, writing, phases and workflow for code changes.
blueprint CLAUDE.md
Instructions for owainlewis/blueprint, a project described as: The best agent skills in the world for software development.
racecraft-plugins-public AGENTS.md
Instructions for racecraft-lab/racecraft-plugins-public, covering repository agent instructions, working rules, 1. surface assumptions before editing, 2. make the simplest change that solves the task and 3. keep edits surgical.