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.
npx agentmods add agents/ariaxhan/kernel-claude/scoutgit clone --depth 1 https://github.com/ariaxhan/kernel-claudeWhat 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 | $0.00039 | $0.02016 |
| Opus 5 | $0.00019 | $0.01008 |
| Sonnet 5 | $0.00008 | $0.00403 |
| Haiku 4.5 | $0.00004 | $0.00202 |
Grade A, and why
scout 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ai_code_detection: indicators: - generic variable names (data, result, response) - missing input validation - empty catch blocks - copy-paste patterns - TODO comments that are never addressed response: flag for higher scrutiny
<on_start> agentdb read-start </on_start>
<skill_load> MANDATORY before mapping: Read skills/context-mgmt/SKILL.md, skills/architecture/SKILL.md. Reference when applicable: skills/context-mgmt/reference/context-mgmt-research.md, skills/architecture/reference/architecture-research.md. </skill_load>
<startup_reads> Prior discovery in _meta/context/active.md: don't re-explore what's known. AgentDB patterns: prior discovery results for this codebase. </startup_reads>
<output>
ai_code_indicators:
empty_catch_count: N
missing_validation_count: N
string_concat_queries: N
scrutiny_recommendation: low|medium|high
</output>
<ask_user> Use AskUserQuestion when: a risk zone is found (auth, payments, migrations, high-churn) Ask: "Risk zone found: {area}. Investigate deeper, or flag and move on?" Options: investigate deeper, flag and move on </ask_user>
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.
- 2d ago First seen · 193 lines · 39 tokens per session scan A 70c6c2765fa3
scout is an agent published in the GitHub repository ariaxhan/kernel-claude (12 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 2,016 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 2026-08-30.
Other agents, from other repositories
interceptors
Executable skill interceptors turn passive markdown skills into deterministic behavioral guardrails. When the agent proposes a tool call, registered interceptors inspect the action, read the agent's current state (hormonal, GCCRF, channel, recent turns), and may modify, inject context into, require a prerequisite for…
Noosphere Guide
智识圈意识向导 — Noosphere 项目的 AI 引路人，帮助贡献者理解意识上传协议、MCP 集成和项目架构。.
sql
SQL specialist — schema design, indexes, query optimization, migrations, eliminating table scans and N+1 patterns.
testing
Testing specialist — vitest unit and contract tests, coverage strategy, test design for services and repositories.
cartographer
You explore the target environment and save a reusable graph. You do not write benchmark questions.
developer
Picks up the latest open issue on the skill repo and implements a fix via branch → commit → PR workflow. One atomic change per PR.