Borrowing it
Nothing to install: this file belongs to victusfate/scaffold. 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/victusfate/scaffold/main/AGENTS.mdgit clone --depth 1 https://github.com/victusfate/scaffoldWrote 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/victusfate/scaffold/agents-md)<a href="https://agentmods.dev/instructions/victusfate/scaffold/agents-md"><img src="https://agentmods.dev/badge/instructions/victusfate/scaffold/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/victusfate/scaffold/agents-md"><img src="https://agentmods.dev/badge/instructions/victusfate/scaffold/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 | $0.07929 | $0.07929 |
| Opus 5.5 | $0.03172 | $0.03172 |
| Sonnet 5.5 | $0.01586 | $0.01586 |
| Haiku 4.5 | $0.00793 | $0.00793 |
Grade A, and why
scaffold AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 561 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines
Harness capabilities
These instructions support Claude Code, Codex, Cursor, Antigravity (agy), and pi. Use the tools actually exposed by the current client. A named tool below is not a guarantee that it is installed. User instructions take precedence over skill defaults; infer routine choices from the repository and existing authorization.
- Skills:
/namebelow denotes a scaffold skill. In Codex, invoke$nameor select it via/skills; read.agents/skills/<name>/SKILL.md, then its linkedskills/<name>.md. Explicitly read referenced@pathfiles relative to the containing document; do not assume Claude's import expansion. - Delegation: use native subagents when available. Respect client concurrency limits by batching independent reviewers. Use fresh context for review when supported; otherwise disclose the limitation and apply the criteria serially. Editing lanes use explicit git worktrees if the client lacks an isolation flag.
- Optional tools: PR subscriptions, monitors, timers, memory, and file-delivery tools depend on the client. Use the fallbacks below; never claim an unavailable integration is active. Do not change global model, trust, or permission settings to make a workflow run.
Session and process ownership
Each session has exactly one orchestrator. Separate sessions may work concurrently, including in the same repository, but they are independent owners. Never inspect, stop, reclaim, interrupt, or signal another session's orchestrator, workers, or a user-launched agent CLI as lifecycle targets. Read-only aggregate resource checks may observe them, but process names, PIDs, terminals, queue owner labels, lease timestamps, and worktrees never establish authority over them.
Only a lifecycle controller may terminate the exact child tree it created for its current generation, and only on explicit cancel or timeout. Normal child completion must not send a cleanup signal. If ownership is ambiguous, leave the process and worktree untouched, stop conflicting dispatch, and report the conflict.
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.
- 7d ago Changed · +15 lines · +265 tokens per session 10353218860c
- 10d ago Changed · +48 lines · +693 tokens per session 772552fb5940
- 16d ago Changed · +21 lines · +347 tokens per session 4ab16cbad3c9
- 17d ago Changed · +1 lines · +17 tokens per session ef3ca3c777ca
- 24d ago Changed · +43 lines · +691 tokens per session a83d852228b5
- 1mo ago Changed · +14 lines · +159 tokens per session 62d90483a42b
- 1mo ago Changed · +29 lines · +433 tokens per session cc138b442a18
- 1mo ago Changed · +75 lines · +1,312 tokens per session abd980f19340
- 1mo ago First seen · 315 lines · 4,012 tokens per session scan A 0a237e6f38f1
scaffold AGENTS.md is an instructions file published in the GitHub repository victusfate/scaffold (6 stars, last pushed 8d ago), licensed MIT. It adds 7,929 tokens to every session, about $0.0317 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 2026-08-31.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.