Borrowing it
Nothing to install: this file belongs to saski/arnesto. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/saski/arnesto/main/.agents/skills/personal-knowledge-routing/SKILL.mdgit clone --depth 1 https://github.com/saski/arnestoWrote 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.
[](https://agentmods.dev/skills/saski/arnesto/personal-knowledge-routing)<a href="https://agentmods.dev/skills/saski/arnesto/personal-knowledge-routing"><img src="https://agentmods.dev/badge/skills/saski/arnesto/personal-knowledge-routing.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00074 | $0.00964 |
| Opus 5 | $0.00037 | $0.00482 |
| Sonnet 5 | $0.00015 | $0.00193 |
| Haiku 4.5 | $0.00007 | $0.00096 |
Grade A, and why
personal-knowledge-routing 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 3d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personal Knowledge Routing
Use this skill to keep agent instructions small while preserving durable knowledge in the personal knowledge vault.
Repositories
- Arnesto checkout (current path):
/Users/saski/Code/arnesto - Personal vault:
/Users/saski/Code/personal-knowledge-vault - Vault content root:
/Users/saski/Code/personal-knowledge-vault/vault
First Files To Read
When working with the vault, start with:
vault/AGENT_GUIDE.mdvault/README.mdvault/_meta/conventions.mdvault/_meta/promotion-policy.mdwhen moving content into more durable areasvault/_meta/source-manifest.mdwhen source material creates or changes durable content- The smallest relevant
vault/maps/*.md,vault/portfolio/*.md, orvault/notes/*.mdfile
Do not read the whole vault unless the user explicitly asks for a full audit.
Routing Table
| Information type | Destination |
|---|---|
| Agent behavior that must apply across tools | Arnesto .agents/rules/ |
| Repeatable agent workflow or protocol | Arnesto .agents/skills/ |
| Tool setup, symlink policy, validation scripts | Arnesto |
| Stable personal facts, preferences, goals, responsibilities, working agreements | personal-knowledge-vault/vault/portfolio/ |
| Durable decisions and decision-making patterns | personal-knowledge-vault/vault/portfolio/decision-log.md or vault/notes/ |
| Distilled reusable knowledge, source summaries, lessons, patterns | personal-knowledge-vault/vault/notes/ |
| Navigation and topic indexes | personal-knowledge-vault/vault/maps/ |
| Raw imports, unprocessed conversations, temporary captures | personal-knowledge-vault/vault/inbox/ |
| Source provenance and promotion decisions | personal-knowledge-vault/vault/_meta/source-manifest.md and vault/_meta/promotion-policy.md |
| Vault schema, conventions, and maintenance policy | personal-knowledge-vault/vault/_meta/ |
Persistence Rules
- Prefer references over copying: if the vault already contains the knowledge, link or cite the file path instead of pasting it into rules.
- Update
portfolio/only when information is stable, reusable, and source-backed. - Apply the vault promotion policy before moving content from
inbox/tonotes/or fromnotes/toportfolio/. - Update the source manifest when a source creates or changes durable notes, portfolio context, maps, or governance files.
- Put uncertain or still-evolving material in
notes/orinbox/first. - Keep raw conversations out of
portfolio/. - Preserve user-authored vault content unless the user explicitly asks for a rewrite.
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.
- 3d ago First seen · 74 lines · 74 tokens per session scan A d7a7742ddd70
personal-knowledge-routing is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed today), licensed Unlicense. It adds 74 tokens to every session and 964 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
immune
Hybrid adaptive memory: Cheatsheet (positive patterns pre-generation) and Immune (negative patterns post-generation) with Hot/Cold tiered auto-learning. Triggers on: "scan for errors", "immune scan", "check output quality", "antibody scan". NOT for PR review (use pr-review) or repo audits (use repo-sentinel).
usage-audit
Audit a Claude Code setup for token waste and context bloat. Checks MCP servers, CLAUDE.md, skills, and settings against bloat filters. Triggers on: "audit my context", "usage audit", "token audit", "context bloat". NOT for codebase audits.
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
agentic-os
A design for running persistent specialist agents, commands, scripts, and file-based memory inside Codex. It keeps the setup in project files so it can continue across sessions.
memory-and-handoff
Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.