Borrowing it
Nothing to install: this file belongs to RockyHong/super-bootstrap. 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/RockyHong/super-bootstrap/main/AGENTS.mdgit clone --depth 1 https://github.com/RockyHong/super-bootstrapWrote 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/rockyhong/super-bootstrap/agents-md)<a href="https://agentmods.dev/instructions/rockyhong/super-bootstrap/agents-md"><img src="https://agentmods.dev/badge/instructions/rockyhong/super-bootstrap/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/rockyhong/super-bootstrap/agents-md"><img src="https://agentmods.dev/badge/instructions/rockyhong/super-bootstrap/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 | $0.00539 | $0.00539 |
| Opus 5.5 | $0.00216 | $0.00216 |
| Sonnet 5.5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
super-bootstrap 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 1mo 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Standing contract for an agent runtime executing a build task in this repo. Routing, verification, doc-sync and commits sit with whoever dispatched it — an orchestrator, or the human who started you directly; this file states what that caller expects back and what stays outside your reach. Sections below are the shipped contract — anything this repo appends under them is binding too.
Ground before building
docs/overview.md— what the product is, its module index and boundaries.docs/techstack.md— stack, architecture rules, the patterns the code already follows.CODING_STANDARDS.md, when the repo carries one — binding conventions; a filled section governs its concern.
Read the files your task names before changing them. Where the task's premise contradicts what you read, report the contradiction instead of building past it.
Build contract
- Finish the work the prompt names, end to end.
- Report it as built, with the exact list of files created or modified.
- Leave version control to the orchestrator: no commit, no staging, no branch, no push, no tag.
- Edit only the surfaces the prompt names. A change you judge necessary elsewhere goes in the report as a recommendation.
While building
- Where a test surface exists, write the failing test first, then make it pass.
- Verify before claiming: run the check, read the output, then state the result.
- Missing context returns as a question in the report — a guess reads as a finding and gets trusted like one.
Not yours
- Narrative docs —
docs/and the rootREADME— belong to the orchestrator's doc-sync step unless the prompt names one as a target. Otherwise report what your change makes stale and leave the edit to the orchestrator. - Work-tracking surfaces: the
docs/work/card set, and theSESSION-STATE/session-carry ledger at the repo root — route to the orchestrator. - Branch, merge and release decisions — route to the orchestrator.
No orchestrator in this run
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.
- 1mo ago Changed · +7 tokens per session 9ccec6cb917c
- 1mo ago Changed · +6 lines · +119 tokens per session 27b1c2f972ee
- 1mo ago First seen · 31 lines · 413 tokens per session scan A e24be10cbfa0
super-bootstrap AGENTS.md is an instructions file published in the GitHub repository RockyHong/super-bootstrap (3 stars, last pushed yesterday), licensed MIT. It adds 539 tokens to every session, about $0.0022 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 2026-09-11.
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).
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.