kioku: Agent for Claude Code

.github/agents/kioku-maintainer.agent.md

Kioku Maintainer is an agent for Claude Code from sandovaldavid/kioku. It costs 34 tokens per session (274 once invoked), scanned A, original, MIT.

A set of maintainer instructions for a .NET MCP server and its generated contracts, skills, client integrations, security boundaries, and optional project memory.

In plain words
What is it for?
Use it when maintaining the Kioku server, changing its contracts or integrations, updating distributed skills, or preparing packages and documentation.
Why use it?
It defines which files and tests are authoritative and sets rules for protecting compatibility, generated files, security, and stored project memory.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions AGENTS.md.

This is sandovaldavid/kioku's own configuration. It tells Claude Code how to work on kioku itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kioku configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sandovaldavid/kioku. 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/sandovaldavid/kioku/main/.github/agents/kioku-maintainer.agent.md
Clone the repo
git clone --depth 1 https://github.com/sandovaldavid/kioku

Made for: Claude Code.

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.

agentmods badge for Kioku Maintainer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sandovaldavid/kioku/kioku-maintainer/github.svg)](https://agentmods.dev/agents/sandovaldavid/kioku/kioku-maintainer)
Your own site
<a href="https://agentmods.dev/agents/sandovaldavid/kioku/kioku-maintainer"><img src="https://agentmods.dev/badge/agents/sandovaldavid/kioku/kioku-maintainer/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.

agentmods 80×15 button for Kioku Maintainer

Your own site · 80×15
<a href="https://agentmods.dev/agents/sandovaldavid/kioku/kioku-maintainer"><img src="https://agentmods.dev/badge/agents/sandovaldavid/kioku/kioku-maintainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 274 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.00274
Opus 5 $0.00017 $0.00137
Sonnet 5 $0.00007 $0.00055
Haiku 4.5 $0.00003 $0.00027

Measured 9d ago against content hash 8062cbb20ec3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

Kioku Maintainer 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 9d 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.

.github/agents/kioku-maintainer.agent.md · 14 lines

What it actually says

Read AGENTS.md and .agents/project-profile.yml before planning or editing. Treat current code, tests, generated contracts, configuration, and executable scripts as authority for implemented behavior.

For substantial work, use Kioku's own globally configured MCP connection plus kioku-project-workflow and kioku-vault. Resolve the exact kioku project before loading or writing memory. Do not confuse the server repository with kioku-obsidian or dotfiles; coordinate changes when bridge contracts or distribution are affected.

Protect filesystem policy, unknown frontmatter preservation, gated capabilities, protocol-safe logging, generated documentation, packaging, and client compatibility. Use skill-distribution-auditor semantics when modifying canonical skills, generated copies, installers, plugins, or adapters.

Do not use the ChatGPT-only workflow skills locally. Do not hand-edit generated contracts, push, merge, rewrite history, or perform destructive vault operations without explicit approval. Run the authoritative .NET, formatting, documentation, and change-specific gates from AGENTS.md, inspect the full diff, and report exact evidence.

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. 9d ago First seen · 14 lines · 34 tokens per session scan A 8062cbb20ec3

Subscribe to this mod's changes

Kioku Maintainer is an agent published in the GitHub repository sandovaldavid/kioku (0 stars, last pushed 5d ago), licensed MIT. It adds 34 tokens to every session and 274 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

FAI Deno Expert

Deno runtime specialist — TypeScript-first with permissions model, Deno KV for edge state, Deno Deploy for serverless, secure-by-default AI service development.

frootai/frootai · 39 tokens

backlog-groomer

For one operator's assigned beads, finds what is ready/urgent to sprint next, proposes cohesive sprint sets from interdependencies, finds duplicates, and surfaces high-priority/urgent-sounding items whose content quality is too low to act on. Full beads mutation authority (merge/close/defer/reject), always…

Apra-Labs/apra-fleet · 79 tokens

vault-explorer

Use proactively when researching what the vault knows about a topic, before creating new notes, or when exploring existing knowledge and connections. Run in foreground — results inform the caller's next steps. Examples: Context: User asks about a topic before creating new content. user: "What does the vault already…

AdrianV101/obsidian-pkm-plugin · 252 tokens

nodejs-backend-engineer

Node.js 24 + TypeScript backend specialist. Build, debug, and scaffold modern Express APIs with Drizzle or Prisma ORM, Vitest TDD test suites, and tsup or Vite 7/8 build pipelines. Use this agent when the user wants to: (1) Create a new Node.js backend project or REST API from scratch (2) Debug TypeScript errors…

karak/karak-claude-plugin · 272 tokens

type-generator

Generates types from schemas, APIs, or data structures including OpenAPI, GraphQL, JSON schemas, and API responses. Use for type generation from various sources.

HKTITAN/cursor-best-practices · 36 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens