What is kodama AGENTS.md?

Repository guidance for Kodama, a pack of specialised AI-agent configurations and reusable workflow instructions. It explains the agent roster, file layout, conventions, and installation lifecycle.

Adding or updating agents and skills, customising the pack for a project, and maintaining its setup and uninstall process.

It helps agents preserve the pack’s naming, architecture, tracked-file, backup, and installation rules when making changes.

How amergrgic/kodama configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to amergrgic/kodama. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/amergrgic/kodama/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/amergrgic/kodama

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/amergrgic/kodama/agents-md/github.svg)](https://agentmods.dev/instructions/amergrgic/kodama/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/amergrgic/kodama/agents-md"><img src="https://agentmods.dev/badge/instructions/amergrgic/kodama/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/amergrgic/kodama/agents-md"><img src="https://agentmods.dev/badge/instructions/amergrgic/kodama/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 673 This file is loaded in full into every session.

When invoked 673 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00673	$0.00673
Opus 5.5	$0.00269	$0.00269
Sonnet 5.5	$0.00135	$0.00135
Haiku 4.5	$0.00067	$0.00067

Measured 1mo ago against content hash 7ea1758cbeb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kodama 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 1mo 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 · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents

This is the kodama agent pack repository. Kodama is the entrypoint; the kodama- prefixed agents are specialists it delegates to.

Architecture

agents/ — self-contained Kiro JSON configs with inline prompts. Each file's name field must match its filename stem.
skills/ — reusable workflow playbooks (Markdown with YAML frontmatter). Referenced by agents via skill:// resource URIs.
setup.sh — lifecycle manager: validates, stages, backs up, installs, and uninstalls. All installed files are tracked in a manifest with SHA-256 hashes.
examples/project-customization/ — shows end users how to extend the pack per-repo.

Agent roster

Agent	Delegates to	Purpose
kodama	all specialists	Plans, delegates, reconciles, verifies
kodama-scout	—	Read-only codebase reconnaissance
kodama-scholar	—	External docs and API research
kodama-sage	—	Architecture, debugging, tradeoffs
kodama-artist	—	UI, UX, accessibility implementation
kodama-smith	—	Bounded implementation and tests
kodama-critic	—	Independent diff review
kodama-forge	—	Infrastructure, CI/CD, deployment
kodama-scribe	—	Documentation and technical writing

Conventions

Agents use model: "auto" — no provider lock-in.
Agents use the universal (V2 + V3) config shape: tools lists both V2 raw names (code, grep, glob, web_search, web_fetch) and V3 category tags (read, write, shell, web), plus permissions.rules alongside the retained toolsSettings. This keeps configs working on Kiro CLI v2, Kiro CLI v3, and the Kiro IDE picker.
allowedTools must be a subset of tools, treating V2/V3 aliases as equal: todo ≡ todo_list, and subagent ≡ subagent/<agent>. The orchestrator's delegation is expressed as explicit subagent/<agent> entries in tools.
Resource paths use __KODAMA_SKILLS_DIR__ as a placeholder; the installer resolves it at install time.
Skills use YAML frontmatter with name (must match directory) and description.
The pack never modifies files outside its own manifest (no global MCP, no other agents).

Read the full file on GitHub · 51 lines

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.

1mo ago Changed · +1 lines · +137 tokens per session 7ea1758cbeb2
2mo ago First seen · 50 lines · 536 tokens per session scan A a89659a48841

Subscribe to this mod's changes

kodama AGENTS.md is an instructions file published in the GitHub repository amergrgic/kodama (12 stars, last pushed 1mo ago), licensed MIT. It adds 673 tokens to every session, about $0.0027 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 2026-08-31.

agent agent-skill agent-skills agentic agents kiro

kodama AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
kodama AGENTS.mdamergrgic/kodama	Instructions file	12	1mo ago	MIT	A	673	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

kodama: Instructions file for Codex