kirok

kirok is a skill for Claude Code, Codex from TadFuji/kirok-mcp. It costs 49 tokens per session (1,092 once invoked), scanned A, original, MIT.

An autonomous memory protocol for the Kirok MCP server, which provides persistent memory across sessions. It instructs the AI to recall relevant information before complex work and retain important lessons afterward.

In plain words
What is it for?
Use it to recall past context before debugging or planning, save new project facts after tasks, and periodically reflect on patterns from completed work.
Why use it?
It helps preserve project decisions, preferences, and known issues instead of losing them between conversations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Good fit Use it to recall past context before debugging or planning, save new project facts after tasks, and periodically reflect on patterns from completed work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tadfuji/kirok-mcp/kirok
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.

Any agent
npx skills add TadFuji/kirok-mcp --skill kirok
Clone the repo
git clone --depth 1 https://github.com/TadFuji/kirok-mcp

Made for: Claude Code, Codex.

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 kirok

README.md
[![agentmods](https://agentmods.dev/badge/skills/tadfuji/kirok-mcp/kirok/github.svg)](https://agentmods.dev/skills/tadfuji/kirok-mcp/kirok)
Your own site
<a href="https://agentmods.dev/skills/tadfuji/kirok-mcp/kirok"><img src="https://agentmods.dev/badge/skills/tadfuji/kirok-mcp/kirok/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 kirok

Your own site · 80×15
<a href="https://agentmods.dev/skills/tadfuji/kirok-mcp/kirok"><img src="https://agentmods.dev/badge/skills/tadfuji/kirok-mcp/kirok.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,092 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 $0.00049 $0.01092
Opus 5 $0.00024 $0.00546
Sonnet 5 $0.00010 $0.00218
Haiku 4.5 $0.00005 $0.00109

Measured yesterday against content hash f1c174908f6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

kirok 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 yesterday.

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.

skills/kirok/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kirok: Fully Autonomous Memory Protocol

You are equipped with Kirok (記録), the next-generation memory system. Kirok provides persistent, cross-session memory via its MCP tools. Your goal is to function as an autonomous "Second Brain." You must proactively manage your memory without needing the user to say "remember this."

Note: Tools are prefixed with KIROK_ (e.g., KIROK_retain, KIROK_recall).


🛑 Core Operational Directives

You must integrate memory operations seamlessly into your standard workflow:

  1. Pre-flight Recall (The "Look Before You Leap" Rule) When a task may touch past decisions, user preferences, or known bugs — debugging, writing a new script, planning an architecture — run KIROK_recall first.
  2. Post-Task Retain (The "Record the Lesson" Rule) When a bug is fixed, a preference is stated, or a milestone is reached, record it with KIROK_retain. If the fact contains credentials, personal data, or anything the user has not agreed to store, check with them before writing it.
  3. Periodic Reflection (The "Wisdom" Rule) If a series of complex tasks has been completed, consider using KIROK_reflect to synthesize underlying patterns into mental models.

🏦 Bank Taxonomy & Fragmentation Prevention

To prevent memory fragmentation (which destroys recall accuracy), keep banks to a small, stable set with broad purposes — do not create arbitrary one-off banks. If your host environment already defines a bank scheme (for example via a project's CLAUDE.md, an existing configuration, or a set of banks already in use), follow that scheme. Otherwise, use these general-purpose banks as a sensible default:

Bank ID Purpose Example Triggers
user-prefs User personal preferences and rules Coding style, language policy (e.g., Japanese for UI), workflow habits
architecture System design and technical specs Tool versions, specific frameworks in use, core logic choices
troubleshooting Error logs, root causes, and fixes "We found why X fails, we must use workaround Y."
milestones Project achievements and work history "Successfully migrated to Next.js on 2026-04-10"
scratch Temporary or volatile memory Unfinished ideas, pending tasks that don't need permanent record

Read the full file on GitHub · 78 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.

  1. yesterday Changed · -9 lines f1c174908f6b
  2. 12d ago First seen · 87 lines · 49 tokens per session scan A 3470fe6759b2

Subscribe to this mod's changes

kirok is a skill published in the GitHub repository TadFuji/kirok-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 1,092 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 skills, from other repositories

context-reconstruct

Re-anchor on the durable record (current-track, live owner thread, pending-questions, relay, buildlog) before acting on anything that depends on earlier context. Read, do not recall.

sonichi/sutando · 43 tokens

lc-curate-context

Decide which files a task actually needs, record that as a reusable llm-context rule, verify it against the codebase - including the files your selection references but leaves out - and pack it for your own context, a chat, or a sub-agent you dispatch. Load when choosing what code to put in front of a model, packing…

cyberchitta/llm-context.py · 90 tokens

session-recap

Reconstruct what happened in a past core session — from a high-level summary down to verbatim owner quotes — by reading the raw session transcripts (complete, crash-proof, unbiased), not the curated relay/handoff notes.

sonichi/sutando · 0 tokens

cortex-automate

Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…

cdeust/Cortex · 93 tokens

cortex-navigate-knowledge

Navigate the knowledge graph — trace entity relationships, explore causal chains, drill into memory clusters, and traverse co-access paths. Use when the user asks 'how are these related', 'what connects X to Y', 'show me the knowledge graph', 'trace the relationship', 'what caused X', 'drill down into', 'explore…

cdeust/Cortex · 95 tokens

cortex-profile

View and manage your cognitive profile — how you think, work patterns, blind spots, and cross-domain connections. Use when the user says 'show my profile', 'how do I work', 'what are my patterns', 'cognitive style', 'blind spots', 'methodology', or at the start of a session to load context. Also use 'rebuild profile'…

cdeust/Cortex · 98 tokens