What is kilo-kit-mcp CLAUDE.md?

A set of instructions for coordinating an AI coding assistant through a two-stage reasoning and execution process. It separates planning and diagnosis from file changes and terminal commands.

Use it to guide task planning, root-cause analysis, code edits, command execution, adversarial review, and managing limited context in supported coding assistants.

It helps prevent code changes before the problem is understood and requires bugs to be traced to their underlying causes first.

How VoDaiLocz/kilo-kit-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to VoDaiLocz/kilo-kit-mcp. 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/VoDaiLocz/kilo-kit-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/VoDaiLocz/kilo-kit-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/vodailocz/kilo-kit-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/vodailocz/kilo-kit-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/vodailocz/kilo-kit-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/vodailocz/kilo-kit-mcp/claude-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/vodailocz/kilo-kit-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/vodailocz/kilo-kit-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 802 This file is loaded in full into every session.

When invoked 802 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	$0.00802	$0.00802
Opus 5	$0.00401	$0.00401
Sonnet 5	$0.00160	$0.00160
Haiku 4.5	$0.00080	$0.00080

Measured 5d ago against content hash 3637100424aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

kilo-kit-mcp CLAUDE.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 5d 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.

CLAUDE.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kilo-Kit C4 v3.0 Cognitive Protocol

Applies to: Claude Code, Antigravity, Gemini CLI, Claude Code, OpenAI Codex

🧠 DIVISION OF LABOR (VỎ NÃO & CHÂN TAY):

Kilo-Kit MCP (Cortex): High-level cognitive reasoning, 5-Whys root cause tracing, Tree-of-Thoughts DAG planning, adversarial red-teaming, context compaction, skill delivery, and SQLite learning memory.
Execution Limbs: Perform surgical changes with defense-in-depth using your native tools or Kilo-Kit tools with Kilo-Sentinel supervision.

🏛️ MANDATORY 5-GATE COGNITIVE PROTOCOL:

Gate 1 (Hard-Gate & Grounded Probe):
- Call MCP tool kilo_orchestrate_task with the user's request as your FIRST action.
- Perform read-only exploratory probing (view_file, grep_search, or kilo_read_file) to build a Grounded Diagnostic Model.
Gate 2 (Substantive Cognitive Reasoning & Benchmarking):
- For Features / Architecture: MUST call kilo_think_step (DAG with 3 trade-off options) and kilo_grill_plan (Adversarial Red-Team stress test). Call kilo_benchmark_solution to audit against industry standards.
- For Bugs / Errors: MUST call kilo_trace_root_cause with { errorLog, failingFile } to extract the 5-Whys causal chain before writing any fix.
- For Context Overload (>4 files read): Call kilo_compact_context to lock invariants and prevent attention degradation.
Gate 3 (Approval & Skill Delivery):
- Call kilo_orchestrate_task with brainstormingApproved=true.
- Load required workflow skills using kilo_get_skill (supports aliases like brainstorming, diagnose, playwright, tdd, clean-code).
- (Optional) Check supervisor status via kilo_sentinel_status.
Gate 4 (Surgical Implementation & Defense-in-Depth):
- Apply problem-solving/defense-in-depth (validation at input, logic, and persistence layers).
- Maintain engineering/clean-code standards with zero bloat.
Gate 5 (4D Quality Assurance & Reflection):
- Dimension 1 (Spec Fidelity): Verify against user requirements using Given-When-Then acceptance criteria (productivity/spec-driven-development).
- Dimension 2 (Clean Code): Verify deep module interfaces and zero dead code (engineering/clean-code).
- Dimension 3 (UX & Aesthetics): Verify responsive layout and mobile touch safety (design/aesthetic, design/mobile-design).
- Dimension 4 (Empirical & Playwright): Run compile/build commands AND execute tests before claiming completion.
- Continuous Reflection: Call kilo_record_reflection with sessionId to persist lessons learned into SQLite memory.

Read the full file on GitHub · 44 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.

5d ago Changed · +8 lines · +109 tokens per session 3637100424aa
9d ago First seen · 36 lines · 693 tokens per session scan A 5d2abe5a117f

Subscribe to this mod's changes

kilo-kit-mcp CLAUDE.md is an instructions file published in the GitHub repository VoDaiLocz/kilo-kit-mcp (26 stars, last pushed today), licensed Apache-2.0. It adds 802 tokens to every session, about $0.0040 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.

Claude Code agent-skills agentic-workflow ai-agent ai-workflows skill-md

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

kilo-kit-mcp: Instructions file for Claude Code