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/bo-516/ide-byebye/agents-mdgit clone --depth 1 https://github.com/bo-516/ide-byebyeWrote 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/bo-516/ide-byebye/agents-md)<a href="https://agentmods.dev/instructions/bo-516/ide-byebye/agents-md"><img src="https://agentmods.dev/badge/instructions/bo-516/ide-byebye/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 | $0.00397 | $0.00397 |
| Opus 5 | $0.00198 | $0.00198 |
| Sonnet 5 | $0.00079 | $0.00079 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
ide-byebye 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 3d 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.
What it actually says
AGENTS.md
Structure & purity
- Prefer pure functions. Side effects (DOM, fs, network, globals) live at the edges, not inside logic.
shared/must run unchanged in both browser and Node: nowindow, nonode:*, no DOM. Cross-env helpers go here so client and server agree on one implementation.server/is Node-only and handles untrusted payloads from the page. Treat every request body as attacker-controlled.- Split a file once it exceeds 200 lines; it MUST be split once it exceeds 400.
Module conventions
- ESM only (
import/export). Norequire, no CommonJS. - Named exports by default;
- Reuse existing helpers (
shared/util.js,dialog-utils.js, etc.) before writing a new one. Don't duplicate truncation, whitespace, locale, or path logic.
Security (do not regress)
- Keep path-containment guards: any page-supplied file path must pass
assertPathInsideRootbefore being read. Neverfsan unresolved path from the page. - Keep the dev-token check on every privileged route; compare tokens in constant time.
- Never widen what the page can reach (arbitrary files, shell, env). If a change needs new server power, call it out explicitly.
User-facing text & prompts
- Prompt text sent to an agent stays language-neutral and is built on the server — don't leak UI locale into it.
Comments
- When you change a function / declared object / component, update its doc comment to match: purpose / responsibility / boundary, each parameter's meaning, the return value, and what breaks if an argument is omitted or wrong.
- Internal (non-exported) units need comments too.
- Comments explain why and boundaries, not a restatement of the code. Keep them English, matching the surrounding style.
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.
- 3d ago First seen · 31 lines · 397 tokens per session scan A 74f7694c48d0
ide-byebye AGENTS.md is an instructions file published in the GitHub repository bo-516/ide-byebye (7 stars, last pushed 9d ago), licensed MIT. It adds 397 tokens to every session, about $0.0020 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
promptscript copilot-instructions.md
Instructions for mrwogu/promptscript, covering github copilot instructions, project, tech-stack, architecture and context.
promptscript testing.instructions.md
Instructions for mrwogu/promptscript, a project described as: Prompt-as-Code for Enterprise AI. Standardize, audit, and deploy instructions across any AI coding assistant.
promptscript typescript.instructions.md
Instructions for mrwogu/promptscript, a project described as: Prompt-as-Code for Enterprise AI. Standardize, audit, and deploy instructions across any AI coding assistant.
ai-prompts AGENTS.md
Instructions for liatrio-labs/ai-prompts, covering ai agent instructions, context marker, local skill scripts, standard workflow and initialize.
agent-done-or-not CLAUDE.md
Instructions for mohamedzhioua/agent-done-or-not, a project described as: Catch your AI agent lying about "done" A one-file proof-gate for Claude Code, Cursor & Codex. it must verify before it can finish.
agent-done-or-not AGENTS.md
Instructions for mohamedzhioua/agent-done-or-not, covering proof-of-done rule (agent-done-or-not) and claim markers (for audit).