kernel-claude AGENTS.md

Instructions for kernel-claude, a project where Claude Code uses persistent memory, multiple agents, and experiments to test which instructions improve its work.

In plain words
What is it for?
Use them when working on kernel-claude tasks that involve memory recall, risk assessment, implementation, delegation, or new failures.
Why use it?
They tell the agent when to recall stored project knowledge, how to judge the risk of a change, and when to break a task into parts before implementing it.

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/ariaxhan/kernel-claude/agents-md
Clone the repo
git clone --depth 1 https://github.com/ariaxhan/kernel-claude

Made for: Codex, OpenCode.

Per session 6,558 This file is loaded in full into every session.
When invoked 6,558 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.06558 $0.06558
Opus 5 $0.03279 $0.03279
Sonnet 5 $0.01312 $0.01312
Haiku 4.5 $0.00656 $0.00656

Measured 2d ago against content hash fa7d9a32602d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kernel-claude AGENTS.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

<block action="report_done_off_commit">"Done" = verified live, not committed. Committed ≠ pushed ≠ deployed ≠ working. Run a verification command (deploy check, curl the served asset, the passing test, the exercised path
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 377 lines

How it starts

The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Location: _meta/agentdb/agent.db Use concrete task nouns, library/subsystem names, discovered paths/symbols, and exact errors or desired outcomes. Recall again after repo inspection reveals better terms, when scope or hypothesis changes, and whenever a new failure appears.

Tier by reversibility × silence × blast radius. File count is only a weak hint. Ambiguous = assume higher tier. Recall from AgentDB at every tier. Implement inline by default; delegate to agents only when the work is heavy and file-disjoint, explicitly requested, or needs independent verification. IF tier >= 2: run $kernel:tearitapart before implementation.

Read the full file on GitHub · 377 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. 2d ago First seen · 377 lines · 6,558 tokens per session scan A fa7d9a32602d

Subscribe to this mod's changes

kernel-claude AGENTS.md is an instructions file published in the GitHub repository ariaxhan/kernel-claude (12 stars, last pushed 2d ago), licensed MIT. It adds 6,558 tokens to every session, about $0.0328 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

causal-memory CLAUDE.md

Instructions for JingxuanC/causal-memory, covering causal memory mcp integration, causal memory integration, after acting on a decision and observing the result, when something fails unexpectedly and when a recorded lesson turns out to be wrong.

JingxuanC/causal-memory · 511 tokens

sqlite-graph-memory AGENTS.md

Instructions for tonydzi/sqlite-graph-memory, covering agents.md — working in this repo, what this repo is, stack and layout, how to verify a change and conventions.

tonydzi/sqlite-graph-memory · 939 tokens

m_flow AGENTS.md

AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).

FlowElement-xinliuyuansu/m_flow · 1,075 tokens

autoharness AGENTS.md

Instructions for tigerless-labs/autoharness: This repo uses Open Knowledge — collaborative markdown via MCP. .open-knowledge/config.yml (with optional /.open-knowledge/config.yml; CLI/env may override) is the path contract: content.dir is the root for relative paths; content.include lists globs that add markdown…

tigerless-labs/autoharness · 2,201 tokens

memex GEMINI.md

Instructions for STiFLeR7/memex, covering memex, agent instructions, execution mode, non-negotiables and what is in scope.

STiFLeR7/memex · 1,338 tokens

second-brain AGENTS.md

Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.

LindaHaviv/second-brain · 1,686 tokens