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/zerodeng01/sublinkpro/agents-mdgit clone --depth 1 https://github.com/ZeroDeng01/sublinkProWhat 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 | $0.05237 | $0.05237 |
| Opus 5 | $0.02618 | $0.02618 |
| Sonnet 5 | $0.01047 | $0.01047 |
| Haiku 4.5 | $0.00524 | $0.00524 |
Grade A, and why
sublinkPro 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 2d 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 — 559 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides AI and human contributors with a high-level architectural guide and navigation map for SublinkPro.
0. MANDATORY PRE-COMMIT VALIDATION - NON-NEGOTIABLE REQUIREMENT
⚠️ ABSOLUTE REQUIREMENT FOR ALL AI AGENTS ⚠️
This is a HARD STOP requirement. No exceptions. No shortcuts. No "will fix later". No "just this once".
Red Line Rule: NO COMMITS WITHOUT VALIDATION
┌─────────────────────────────────────────────────────────────┐
│ 🛑 BLOCKING REQUIREMENT - READ THIS FIRST │
├─────────────────────────────────────────────────────────────┤
│ │
│ BEFORE any git commit, git add, or PR creation: │
│ │
│ 1. You MUST invoke: pre-commit-check skill │
│ 2. You MUST execute ALL applicable validation commands │
│ 3. You MUST fix ALL failures before proceeding │
│ 4. You MUST document what was validated │
│ │
│ Violations of this rule constitute incomplete work. │
│ │
└─────────────────────────────────────────────────────────────┘
Mandatory Trigger Points
You MUST invoke .agents/skills/pre-commit-check/SKILL.md BEFORE:
- Running
git addorgit commit- Whether initiated by you or requested by user - Creating or updating a PR - Via
gh pr createor any PR command - Declaring work "complete", "done", or "finished" - In any form
- User explicitly asks to commit - Even if they say "skip checks" (refuse and explain why)
- Any code change is ready for commit - Backend, frontend, docs, config, or mixed
The Validation-Before-Commit Workflow
Code Change Complete
↓
├─> Did you invoke pre-commit-check skill?
│ ├─> NO → STOP. Invoke it now. DO NOT PROCEED.
│ └─> YES → Continue
↓
├─> Did ALL validation commands pass?
│ ├─> NO → STOP. Fix failures. Re-run validation. DO NOT PROCEED.
│ └─> YES → Continue
↓
├─> Did you stage ONLY intended changes?
│ ├─> NO → STOP. Review staged files. Remove unintended. DO NOT PROCEED.
│ └─> YES → Continue
↓
├─> Did you prepare a proper commit message?
│ ├─> NO → STOP. Prepare semantic commit message. DO NOT PROCEED.
│ └─> YES → Continue
↓
Ready to Commit (present to user for final review)
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.
- 2d ago First seen · 559 lines · 5,237 tokens per session scan A a84085e8ef53
sublinkPro AGENTS.md is an instructions file published in the GitHub repository ZeroDeng01/sublinkPro (1,605 stars, last pushed yesterday), licensed MIT. It adds 5,237 tokens to every session, about $0.0262 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-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.
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).
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 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).
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.