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/nanako0129/tokenbar/agents-mdgit clone --depth 1 https://github.com/Nanako0129/TokenBarWrote 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/nanako0129/tokenbar/agents-md)<a href="https://agentmods.dev/instructions/nanako0129/tokenbar/agents-md"><img src="https://agentmods.dev/badge/instructions/nanako0129/tokenbar/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 | $0.00612 | $0.00612 |
| Opus 5 | $0.00306 | $0.00306 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
TokenBar 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.
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.
TokenBar agent routing
docs/knowledge/is the canonical project knowledge base. This adapter routes work to it; it does not copy project facts.
Read docs/knowledge/README.md for every task before the task-specific document below. If .agent-local/AGENTS.md exists, read it after the canonical documents as additive machine-local guidance only; it must not override canonical architecture, verification, authorization, or release rules.
Read order
| Task | Required reading |
|---|---|
| Any task | docs/knowledge/README.md, then the task-specific row below |
| Rust, C ABI, or Swift data flow | docs/knowledge/architecture.md |
| Branches, reviews, merge, or release authorization | docs/knowledge/workflow.md |
| Tests, fixtures, cache invalidation, or cross-language checks | docs/knowledge/verification.md |
| Shared tokscale engine or consumer pin | vendor/AGENTS.md, vendor/README.md, docs/knowledge/vendor-tokscale.md |
| Release, Sparkle, appcast, or Homebrew | docs/knowledge/release.md |
| GitHub prose or contributor credit | docs/knowledge/communication.md |
| Current maintenance priorities | docs/knowledge/current-state.md |
Invariants
| Invariant | Rule |
|---|---|
| Source of truth | Add canonical project facts to docs/knowledge/; keep adapters as routing and guardrails. |
| Cross-language seam | Preserve the Rust -> C ABI -> Swift contract; verify both sides when a boundary changes. |
| Pre-aggregation | Do not attempt to remove a contribution after a mixed aggregate has been computed; pass the filter to the producer. |
| Shared-engine boundary | Land shared Rust changes in tokscale-core; advance only a reviewed gitlink, and keep app-owned FFI, C ABI, Swift, and build wiring in TokenBar. |
| Public repository | Never add private paths, credentials, machine-specific tooling details, or unpublished security work to tracked docs. |
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 · 37 lines · 612 tokens per session scan A 60455676da11
TokenBar AGENTS.md is an instructions file published in the GitHub repository Nanako0129/TokenBar (309 stars, last pushed 4d ago), licensed MIT. It adds 612 tokens to every session, about $0.0031 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
microsandbox AGENTS.md
AGENTS.md instructions for superradcompany/microsandbox, covering agents.md, scope, project map, design principles and backward compatibility review.
AIBattery CLAUDE.md
Instructions for KyleNesium/AIBattery, covering ai battery — ai agent guide, spec-driven workflow, build & run, bundle and launch and testing.
turso AGENTS.md
Instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
ton-rs AGENTS.md
Instructions for ston-fi/ton-rs, covering ton-rs agent guide, repository, boundaries, public api and ton invariants.