Borrowing it
Nothing to install: this file belongs to damienbenveniste/ScaffoldGuard. 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/damienbenveniste/ScaffoldGuard/main/AGENTS.mdgit clone --depth 1 https://github.com/damienbenveniste/ScaffoldGuardWrote 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/damienbenveniste/scaffoldguard/agents-md)<a href="https://agentmods.dev/instructions/damienbenveniste/scaffoldguard/agents-md"><img src="https://agentmods.dev/badge/instructions/damienbenveniste/scaffoldguard/agents-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 | $0.04254 | $0.04254 |
| Opus 5 | $0.02127 | $0.02127 |
| Sonnet 5 | $0.00851 | $0.00851 |
| Haiku 4.5 | $0.00425 | $0.00425 |
Grade A, and why
ScaffoldGuard AGENTS.md scanned grade A with 1 finding 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 8d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Use `subprocess.run` without `shell=True` for command execution. How it starts
The opening of the file, as written. The whole thing — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
These rules apply to every code, test, documentation, template, and configuration change in this repository.
Product Orientation
- Build
scaffold-guard: a PyPI-installable Python CLI that generates strict starter repositories designed for safe coding-agent collaboration. - Public user-facing docs should present
uv tool install scaffold-guardfollowed by the installedscaffold-guardcommand. Do not advertise transient no-install execution paths,uvx, oruv run scaffold-guard ...in user-facing install or quickstart flows. Keepuv run scaffold-guard ...only for repo-local development, CI, or generated agent operating instructions when project-local dependency resolution is required. - Preserve the V1 promise: generate a repository with clear agent instructions,
strict local tooling, GitHub Actions or GitLab CI, and policy checks that
catch common agent mistakes. The default
minimalprofile should add guardrails only;pythonshould be explicit when users want Python package folders and tooling;typescriptandmonoreposhould be explicit when users want TypeScript or mixed Python+TypeScript starter layouts. - New monorepo projects should use semantic workspace layouts:
applicationgeneratesapps/apiandapps/web,librarygeneratespackages/coreandpackages/client, andcustomrequires two explicit safe relative paths. Preserve recorded workspace paths when upgrading existing projects; never rename or move user-owned seed directories automatically. - Keep
scaffold-guard initfriendly for first-time users: omittingNAMEstarts guided setup, and leaving the project-name prompt blank initializes the current empty directory. PassingNAMEand flags remains the stable automation path. Keep.as a compatibility alias for current-directory automation, but do not present it as the primary guided user flow. Do not add guided-only generation behavior without matching non-interactive flags. - Guided setup should present meaningful setup choices, not one yes/no prompt per mature tool when a preset or scoped selector is clearer. Keep Python and TypeScript tool prompts profile-aware, and keep generated files, config, CI, validation, docs, and agent instructions synchronized with those choices.
- Keep V1 focused on a developer CLI. Do not add a SaaS dashboard, telemetry, external AI calls, complex YAML DSL, plugin ecosystem, package/release publish automation, or automatic mutation of mature existing repositories. A guarded git commit/push wrapper is acceptable only when it validates, refuses mixed scope, and requires explicit user intent.
- When generated instructions, Codex rules, CI, or docs depend on a
ScaffoldGuard command added after the initial release, define its minimum
supported ScaffoldGuard version in one shared code constant and render that
dependency floor into every generated project profile that can invoke it. Use
project-local
uv run scaffold-guard ...command forms when stale global installs could shadow the generated dependency. - Always generate
AGENTS.mdfor scaffolded projects. Treat it as the shared cross-agent instruction source. - Keep adapter behavior explicit:
- Codex uses
AGENTS.mdfor behavior. - Claude Code uses
CLAUDE.mdas a wrapper that importsAGENTS.md, with optional.claude/rules/. - Cursor uses
.cursor/rules/*.mdcplusAGENTS.md.
- Codex uses
- Prefer small, shippable V1 behavior over speculative framework design.
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.
- 8d ago First seen · 372 lines · 4,254 tokens per session scan A 4ded518ac514
ScaffoldGuard AGENTS.md is an instructions file published in the GitHub repository damienbenveniste/ScaffoldGuard (7 stars, last pushed 20d ago), licensed MIT. It adds 4,254 tokens to every session, about $0.0213 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
spec-kit AGENTS.md
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.