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/voytechg/spec-driven-development/agents-mdgit clone --depth 1 https://github.com/VoytechG/spec-driven-developmentWhat 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 | $0.00529 | $0.00529 |
| Opus 5 | $0.00264 | $0.00264 |
| Sonnet 5 | $0.00106 | $0.00106 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
spec-driven-development 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 yesterday.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spec-driven-development — Contributor Notes
These notes apply to anyone (human or agent) editing this plugin repo. They do not apply to projects that consume the plugin.
Scope
The plugin is generic. It must contain no references to specific projects, products, codebases, employers, or domains. The only allowed exceptions are inside docs/specs/ design notes, which are historical context.
What the plugin ships
- Five skills:
using-spec-driven-development,load-project-context,maintain-project-docs,review-project-history, andupdate-docs-structure. - Three hooks:
SessionStart,UserPromptSubmit, andStop. - Markdown templates under
templates/. - Three platform manifests: Claude Code, Codex, Gemini CLI.
- One marketplace logo under
assets/.
Every change should leave this list intact unless the change deliberately adds or removes one of these pieces.
Style
- Tight, specific prose. The plugin sells concise documentation; practice it here too.
- No emojis in markdown content.
- Hook scripts:
set -euo pipefail,printf(not heredoc), shellcheck-clean, extensionless filenames. - Skill
SKILL.md: YAML frontmatter withnameanddescriptiononly; imperative-mood body; no padding. - Templates: section headers plus a one-line italic hint per section. No placeholder paragraphs.
Versioning
- Bump
versionin all four manifests together:package.json,.claude-plugin/plugin.json,.claude-plugin/marketplace.json,.codex-plugin/plugin.json,gemini-extension.json. - Add a
RELEASE-NOTES.mdentry per release.
Local checks
bash -n hooks/session-start,bash -n hooks/user-prompt-submit, andbash -n hooks/stopmust pass.- Run
hooks/session-startfrom a throwaway repo withAREAS.mdand from a directory withoutAREAS.md;bash -ndoes not catch every runtime quoting issue. - Run
hooks/user-prompt-submitonce with a project-work prompt and once with a non-project prompt. - Run
hooks/stoponce in a throwaway repo with code-only changes and once after adding a docs change. - JSON manifests must parse.
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.
- yesterday First seen · 45 lines · 529 tokens per session scan A dbca5e880e0f
spec-driven-development AGENTS.md is an instructions file published in the GitHub repository VoytechG/spec-driven-development (4 stars, last pushed 3mo ago), licensed MIT. It adds 529 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 2026-08-31.
Other instructions, from other repositories
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.
buildNext
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.