Borrowing it
Nothing to install: this file belongs to semantic-craft/iOS-vibebuddy. 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/semantic-craft/iOS-vibebuddy/main/AGENTS.mdgit clone --depth 1 https://github.com/semantic-craft/iOS-vibebuddyWrote 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/semantic-craft/ios-vibebuddy/agents-md)<a href="https://agentmods.dev/instructions/semantic-craft/ios-vibebuddy/agents-md"><img src="https://agentmods.dev/badge/instructions/semantic-craft/ios-vibebuddy/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/semantic-craft/ios-vibebuddy/agents-md"><img src="https://agentmods.dev/badge/instructions/semantic-craft/ios-vibebuddy/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 | $0.00850 | $0.00850 |
| Opus 5.5 | $0.00340 | $0.00340 |
| Sonnet 5.5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
iOS-vibebuddy 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 15d 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 — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Agent-facing configuration for the iOS-vibebuddy repo. Global rules apply first; this file adds project facts.
Delivery boundaries
The task goal authorizes the delivery steps it includes: installation, the production port :9876, login-token setup under ~/Library/Application Support/vibebuddy/, release, or cross-machine sync, without separate per-step approval. Check shared-app ownership before replacing /Applications/VibeBuddyMacApp.app: it is one copy shared by every session on this Mac, and replacing it kills any real-device acceptance another session is running — check for a peer run first (docs/sparkle-setup.md, § The installed app is shared). If a peer is using that copy, defer replacement, continue independent work, and report the remaining installation step. Configured credentials may be used for an authorized operation; reading secrets for context is not implied.
Before changing app or daemon behavior, running app/daemon acceptance, or claiming verification complete, read Verification in CODING_STANDARDS.md. Apply its affected-flow end-to-end standard, isolated runtime boundary, and explicit treatment of unavailable real-device or installed-app acceptance.
Skills
Repository-owned skills live in docs/agents/skills/ and are tracked here: verify-vibebuddy (isolated runtime acceptance), vibebuddy-history (resuming from handoff notes and vibebuddy-mcp facts), vibebuddy-handoff (source-identified handoff notes). For these three skills, .agents/skills/<name> is an untracked relative link to ../../docs/agents/skills/<name>; .claude/skills/ points to that face and also stays untracked.
Task references
| Work | Reference |
|---|---|
| Finding owning source, choosing scoped checks, or recording delivery evidence | docs/agents/development.md; executable profiles: tools/check.py --list |
Creating, reading, or updating tickets and PRDs — tracked Markdown under docs/planning/backlog/<feature>/ with an index row, not GitHub Issues and not .scratch/; a skill's "publish to the issue tracker" means writing and committing that file |
docs/agents/issue-tracker.md |
Assigning or changing triage state (needs-triage, needs-info, ready-for-agent, ready-for-human, wontfix as a Status: line) |
docs/agents/triage-labels.md |
Changing domain behavior, terminology, or architecture (single-context layout: GLOSSARY.md + docs/adr/) |
docs/agents/domain.md, GLOSSARY.md, and the relevant ADRs; flag a conflict with an existing ADR before implementing against it |
| Resuming earlier work ("上次", "昨天", "继续") | docs/agents/skills/vibebuddy-history/SKILL.md: newest handoff note first, then vibebuddy-mcp facts for its source session to check drift, then show for that session's transcript only where the note leaves gaps. There is no archive or search of past conversations. Optional status --exclude-session reports other sessions in this checkout; report them and let the user decide. The tools are read-only |
| Writing a source-identified handoff | docs/agents/skills/vibebuddy-handoff/SKILL.md: run vibebuddy-mcp facts for the writer's own session key first and place its block at the top |
Opening or merging a pull request to main — review with an independent AGY CLI Gemini session first, post the verdict on the PR; no bot review, no required checks |
docs/agents/pr-review.md |
| Planning the next cycle or changing macOS distribution, sandboxing, or agent integration | docs/agents/mac-app-store.md: retained design/research; Store tickets closed by owner, not the next execution queue |
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.
- 15d ago Changed · +5 tokens per session 481809ff0e30
- 20d ago Changed · -8 lines · -175 tokens per session 7d0e29c36c8c
- 22d ago Changed · +3 tokens per session 38aaaaa549e4
- 23d ago Changed · +26 tokens per session d4c343fd5066
- 24d ago Changed · -3 lines · +6 tokens per session e85ac2bb3006
- 26d ago Changed 827809962cb1
- 1mo ago Changed · -9 tokens per session 108bfc26ddd0
- 1mo ago Changed · +22 tokens per session 8a68ce69e024
- 1mo ago Changed · +54 tokens per session 76caff9f6a5a
- 1mo ago First seen · 38 lines · 918 tokens per session scan A 6f0e35c98ab0
iOS-vibebuddy AGENTS.md is an instructions file published in the GitHub repository semantic-craft/iOS-vibebuddy (92 stars, last pushed 14d ago), licensed MIT. It adds 850 tokens to every session, about $0.0034 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 2026-08-30.
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.