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/longyijdos/kana/agents-mdgit clone --depth 1 https://github.com/longyijdos/kanaWrote 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/longyijdos/kana/agents-md)<a href="https://agentmods.dev/instructions/longyijdos/kana/agents-md"><img src="https://agentmods.dev/badge/instructions/longyijdos/kana/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 | $0.00962 | $0.00962 |
| Opus 5 | $0.00481 | $0.00481 |
| Sonnet 5 | $0.00192 | $0.00192 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade A, and why
kana 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 4d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Scope and workflow
- Choose a change scope that matches the task and keep the result cohesive.
- Default to completing the task in one pass. Do not impose separate implementation, review, test, or documentation phases unless the user requests a checkpoint.
- Do not stop for routine approval. Ask for direction only when a missing choice would materially change the result, broaden the scope, or authorize a consequential action.
- Avoid unnecessary churn. For larger features or refactors, explain the important design tradeoffs and keep related changes together.
- Do not blindly follow a brittle or overly complex request. Explain the maintenance concern and suggest the simplest durable alternative.
- Before an unfamiliar or cross-module change, read
docs/architecture.mdand usedocs/README.mdto find the canonical owner; for a narrow change, read only the relevant owner document and avoid loading unrelated documentation.
Implementation
- Prefer clear names and code structure over comments.
- Add comments only for non-obvious invariants, design decisions, protocol semantics, ordering requirements, provider-specific behavior, and mutable state boundaries.
- Keep implementation comment blocks within four lines and 320 characters. Do not add comments that restate the code.
- Put longer explanations in documentation only when they describe a stable contract or design boundary that future contributors need.
- Do not add
comment-check-ignoresuppressions without maintainer approval. - For imports under
src, use relative imports within the same top-levelsrcdirectory. Use the@/alias only across top-level directories and prefer target barrels such as@/coreor@/toolsover deep aliases.
Tests
- Treat tests as evidence for behavior, not as mandatory file churn for every code edit.
- When observable behavior changes, inspect existing coverage first. Add or update tests only where the current suite does not adequately cover the changed contract or regression risk.
- Add a regression test for a bug fix when it is practical, stable, and likely to prevent recurrence.
- Do not change tests solely because implementation structure, comments, formatting, documentation, or generated references changed while behavior remained covered.
- Before adding a case, identify the lowest behavior owner and search existing coverage. Prefer strengthening or consolidating an existing case when it remains independently readable.
- Keep complete input and error matrices at the lowest owning layer. Higher-level tests should cover representative wiring and cross-module behavior instead of repeating those matrices.
- Run checks in proportion to the change. Use the full
bun run checkfor broad, risky, or commit-ready changes.
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.
- 4d ago First seen · 52 lines · 962 tokens per session scan A 31898fbc4663
kana AGENTS.md is an instructions file published in the GitHub repository longyijdos/kana (5 stars, last pushed 6d ago), licensed MIT. It adds 962 tokens to every session, about $0.0048 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
oh-my-pi AGENTS.md
AGENTS.md instructions for can1357/oh-my-pi, covering development rules, default context, package structure, github and code quality.
tinycode AGENTS.md
AGENTS.md instructions for bobbyjohnstx/tinycode, covering commits and pr titles, style guide, general principles, destructuring and variables.
DeepCopilot copilot-instructions.md
Instructions for deep-copilot/DeepCopilot, covering deepcopilot 项目级 copilot / ai 审核指引, 项目概述, 技术栈, 审查时必须关注的红线 and 代码风格.
tinycode CLAUDE.md
Claude Code instructions for bobbyjohnstx/tinycode, covering claude.md, commands, install dependencies (from repo root, development only), run in development (tui mode) and other dev modes.
Archon AGENTS.md
AGENTS.md instructions for coleam00/Archon, covering working on archon, read before changing code, product boundaries, engineering taste and prefer the smallest truthful system.
Archon CLAUDE.md
Claude Code instructions for coleam00/Archon, a project described as: The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.