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/pisberg/vibetags/agents-mdgit clone --depth 1 https://github.com/PIsberg/vibetagsWrote 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/pisberg/vibetags/agents-md)<a href="https://agentmods.dev/instructions/pisberg/vibetags/agents-md"><img src="https://agentmods.dev/badge/instructions/pisberg/vibetags/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 5.1 | $0.02683 | $0.02683 |
| Opus 5 | $0.01341 | $0.01341 |
| Sonnet 5 | $0.00537 | $0.00537 |
| Haiku 4.5 | $0.00268 | $0.00268 |
Grade A, and why
vibetags 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 yesterday.
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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VibeTags — Agent Instructions
Start with llms.txt for a map of this repo's docs and layout.
The primary agent briefing is CLAUDE.md — build commands, build
order, architecture invariants, and the <project_guardrails> block (locked
files, contract-frozen signatures, hot-path constraints). It is tool-neutral
despite the name: read and follow it whichever agent you are.
Ground rules for any agent working here:
- Respect the guardrails in CLAUDE.md: never edit files/elements listed as locked, never change contract-frozen signatures.
- Never hand-edit content between
VIBETAGS-START/VIBETAGS-ENDmarkers in any file — it is generated by this project's own annotation processor. - Build order matters:
vibetags-annotations→vibetags→vibetags-bom→example. Always build from the subproject's own directory. - Reference docs load on demand:
docs/ANNOTATIONS.md(annotation reference),docs/PLATFORMS.md(output-file table),docs/TESTS.md(test coverage map),docs/ARCHITECTURE.md(deep dive),docs/DEPENDENCIES.md(third-party artifacts).
Note: this file is intentionally not VibeTags-managed — other AI config files exist at the root, so the processor's AGENTS.md sole-file fallback leaves it untouched.
AUTO-GENERATED AI RULES
Generated by VibeTags | https://github.com/PIsberg/vibetags
Do not edit manually.
LOCKED FILES (DO NOT EDIT)
- se.deversity.vibetags.processor.AIGuardrailProcessor.generateFiles(): Step order is load-bearing: fingerprint check → sidecar write → sidecar read → merge → file write → cache flush; reordering steps silently skips regeneration or corrupts multi-module output
- se.deversity.vibetags.processor.internal.TransitiveManifest.RESOURCE_PACKAGE: Must stay a valid Java package name. javac's CLASS_PATH location skips archive directories that are not package identifiers, so moving these manifests under META-INF/ leaves Filer.getResource listing zero entries and transitive discovery fails silently while the conventional location looks correct. TransitiveManifestPathTest pins the working path.
- se.deversity.vibetags.processor.model.GuardrailAnnotations.ALL: Append only. This order fixes the insertion order of every LinkedHashSet downstream, so reordering or removing an entry rewrites generated files in every consuming build, with nothing failing to name the cause. BuildFingerprint hashes in its own separately pinned order; the two are not the same list and must not be aligned.
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.
- yesterday Changed · +1 lines · +86 tokens per session 6a0028846b5b
- 5d ago First seen · 96 lines · 2,597 tokens per session scan A 112bf454268d
vibetags AGENTS.md is an instructions file published in the GitHub repository PIsberg/vibetags (15 stars, last pushed yesterday), licensed MIT. It adds 2,683 tokens to every session, about $0.0134 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
tachyon GEMINI.md
Gemini CLI instructions for kpavlov/tachyon: In repositories indexed by CodeGraph (a .codegraph/ directory exists at the repo root), reach for it BEFORE grep/find or reading files when you need to understand or locate code.
McpServer AGENTS.md
AGENTS.md instructions for sharpninja/McpServer, covering agent instructions, session start, rules, byrd test gate and where things live.
AmbyKit CLAUDE.md
Claude Code instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.
mcp-execution mcp-wasm-runtime.instructions.md
Instructions for bug-ops/mcp-execution, covering copilot instructions: mcp-wasm-runtime, security - critical, security principles, security configuration and host function safety.
mcp-ai-wpoos CLAUDE.md
Claude Code instructions for nvdigitalsolutions/mcp-ai-wpoos, covering nv oos (open operator system) — claude code context, related files, what this is, php compatibility — critical and naming conventions.
skillsync-mcp CLAUDE.md
Instructions for adityasugandhi/skillsync-mcp, covering claude.md, project overview, development commands, architecture and key files.