Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/zkysar1/claude-mind/tree)<a href="https://agentmods.dev/skills/zkysar1/claude-mind/tree"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/tree.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 | $0.00176 | $0.16542 |
| Opus 5 | $0.00088 | $0.08271 |
| Sonnet 5 | $0.00035 | $0.03308 |
| Haiku 4.5 | $0.00018 | $0.01654 |
Grade B, and why
tree scanned grade B 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 6d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
> grep `.claude/` for any moved path. How it starts
The opening of the file, as written. The whole thing — 1,217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/tree — Knowledge Tree Operations
System skill (NOT user-invocable) that provides all knowledge tree operations as
discoverable sub-commands. Replaces the former /tree-growth skill and extends it
with granular read/write operations that any skill can call.
Supports recursive knowledge tree at arbitrary depth up to D_max=20.
Mode Gate for Write Operations
For sub-commands: add, edit, set, decompose, split-overcap, distill, maintain, reparent
Bash: session-mode-get.sh
- If mode is
reader: output "Tree write operations require assistant mode. Run/start --mode assistantto enable." STOP. - If mode is
assistantorautonomous: PROCEED. Read-only sub-commands (read, find, stats, validate) work in all modes.
Sub-Commands
/tree read <key> — Read node content + _tree.yaml metadata
/tree find <query> — Find best-matching nodes (wraps tree-find-node.sh)
/tree add <parent> <key> <summary> — Create a new child node (atomic: _tree.yaml + .md)
/tree edit <key> — Read node for editing, update _tree.yaml after
/tree set <key> <field> <value> — Update _tree.yaml metadata field
/tree decompose <key> — Break a large node into children
/tree split-overcap <key> --boundaries "..." — Verbatim split of a node too big to Read
/tree distill <key> — Extract actionable kernel, archive narrative
/tree maintain — Full batch maintenance (DECOMPOSE, REDISTRIBUTE, DISTILL, SPLIT, SPROUT, MERGE, PRUNE, RETIRE)
/tree reparent <node> <new-parent> — Move node (and subtree) to a new parent
/tree stats — Tree health overview
/tree validate — Consistency check
File Path Convention
Node files live at paths derived from their ancestry in _tree.yaml:
L1: world/knowledge/tree/{L1-domain}.md
L2: world/knowledge/tree/{L1}/{L2-topic}.md
L3: world/knowledge/tree/{L1}/{L2-topic}/{L3-subtopic}.md
L4: world/knowledge/tree/{L1}/{L2-topic}/{L3}/{L4-detail}.md
...
LN: world/knowledge/tree/{L1}/{L2}/.../{LN-detail}.md (up to D_max=20)
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.
- 6d ago First seen · 1,217 lines · 176 tokens per session scan B 39085b1534c2
tree is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed today), licensed MIT. It adds 176 tokens to every session and 16,542 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
hive.context-preservation
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
learning-capture
Log corrections, errors, and discoveries to orbital/LESSONS.md so future sessions avoid repeating mistakes.
obsidian
Obsidian: работа с заметками и базой знаний.
memory-system
3-tier hierarchical memory management for AI agents. L1 (daily active context, 100 lines), L2 (weekly decisions/insights, 400 lines), L3 (long-term archive, unlimited). Includes self-improvement loop, session continuity, semantic search, and mistake-tracking. Use when starting a session (load memory), ending a session…