katana AGENTS.md

Project instructions for Katana, a deterministic tool that analyses and applies code refactoring plans across different programming languages and toolchains. They define its runtime, ownership boundaries, compatibility requirements, and agent contract.

In plain words
What is it for?
Use them when changing Katana's document model, planning or applying refactors, language and tool adapters, command protocols, CLI behavior, or compatibility tests.
Why use it?
They reduce the risk of breaking existing command formats, language adapters, formatting tools, or safety rules when modifying Katana.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/vgmakeev/katana/agents-md
Clone the repo
git clone --depth 1 https://github.com/vgmakeev/katana

Made for: Codex, OpenCode.

Per session 397 This file is loaded in full into every session.
When invoked 397 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash d90329bc4940, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

katana 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 2d 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.

AGENTS.md · 46 lines

What it actually says

Agent instructions

Katana is an agent-first, deterministic polyglot refactoring executor.

Runtime

  • Use Python 3.14.
  • Install with uv sync --all-groups.
  • Run the complete gate with make check.
  • Run make markdown-check when the Node bridge changes.

Boundaries

  • Core owns DocumentIR, plans, conformance, apply orchestration, and the CLI.
  • Language behavior belongs in katana.adapters.<stack> or an external package registered under katana.adapters.
  • Formatter, lint-fix, and checker behavior belongs in katana.toolchains.<stack> or katana.toolchains entry points.
  • Built-in adapters use the same public contracts as third-party adapters.
  • Command adapter protocol v1 is analysis-only and must fail rewrite closed.

Compatibility

  • Preserve split-plan v1 and existing schema, outline, assess, plan, apply, large, and project JSON behavior.
  • Keep legacy adapter ids node_typescript, dart_analyzer, and node_postcss.
  • Existing public functions remain compatibility facades over adapters.
  • Add conformance and regression tests for protocol changes.

Agent contract

  • Never include source bodies in DocumentIR or other agent maps.
  • Keep commands non-interactive and machine-readable.
  • Prefer exact hashes and byte spans over parser-specific node objects.
  • Analysis-only support is useful; do not claim rewrite capabilities without dependency closure, import handling, formatting, and validation.
  • Preserve source bytes during mechanical moves. Semantic changes are separate.

Source budget

  • Keep source files within 500 physical and language-aware code lines.
  • The hard repository ceiling is 500 lines.
  • make size-check enforces both measures across runtime, tests, and examples.
  • Split by cohesive responsibility before raising the ceiling or adding exclusions.
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.

  1. 2d ago First seen · 46 lines · 397 tokens per session scan A d90329bc4940

Subscribe to this mod's changes

katana AGENTS.md is an instructions file published in the GitHub repository vgmakeev/katana (12 stars, last pushed 12d ago), licensed Apache-2.0. 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 2026-08-30.

Related

Other instructions, from other repositories

jcodemunch-mcp CLAUDE.md

Claude Code instructions for jgravelle/jcodemunch-mcp, covering jcodemunch-mcp — project brief, current state, key files, cli subcommands and architecture notes.

jgravelle/jcodemunch-mcp · 34,089 tokens

ariadne AGENTS.md

Instructions for CRJFisher/ariadne, covering guidelines, project layout / intention tree, refactoring ethos, documentation style: canonical and self-contained and scope.

CRJFisher/ariadne · 1,990 tokens

ariadne CLAUDE.md

Instructions for CRJFisher/ariadne, covering guidelines, goals, project layout / intention tree, refactoring ethos and processing pipeline.

CRJFisher/ariadne · 1,330 tokens

jcodemunch-mcp AGENTS.md

AGENTS.md instructions for jgravelle/jcodemunch-mcp, covering code exploration policy, session-aware routing and model-driven tool tiering.

jgravelle/jcodemunch-mcp · 1,312 tokens

coldstart CLAUDE.md

Instructions for AkashGoenka/coldstart: Lightweight navigation layer for AI agents. Answers one question: which files are relevant to this task? Fast static index over file paths, symbol names, and exports — queried via two operations, find (ranked file paths matched against declared names: filenames, path segments…

AkashGoenka/coldstart · 6,203 tokens

codemap AGENTS.md

Instructions for stainless-code/codemap, a project described as: Cut AI-agent token waste 90% — query a local SQLite structural index of your JS/TS/CSS codebase with SQL in one round-trip instead of 3–5 file reads. Symbols, imports, calls, components, CSS tokens, coverage, markers. CLI, MCP (21 tools), HTTP, GitHub…

stainless-code/codemap · 632 tokens