Borrowing it
Nothing to install: this file belongs to zkysar1/Claude-Mind. 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/zkysar1/Claude-Mind/main/.claude/skills/reflect-tree-update/SKILL.mdgit clone --depth 1 https://github.com/zkysar1/Claude-MindWrote 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/reflect-tree-update)<a href="https://agentmods.dev/skills/zkysar1/claude-mind/reflect-tree-update"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/reflect-tree-update/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.
<a href="https://agentmods.dev/skills/zkysar1/claude-mind/reflect-tree-update"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/reflect-tree-update.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00093 | $0.01778 |
| Opus 5 | $0.00046 | $0.00889 |
| Sonnet 5 | $0.00019 | $0.00356 |
| Haiku 4.5 | $0.00009 | $0.00178 |
Grade A, and why
reflect-tree-update scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/reflect-tree-update — Tree Update Protocol
This sub-skill implements the shared Tree Update Protocol used by /reflect-on-outcome (Hypothesis mode) and /reflect-on-self (Patterns mode). It is invoked after any reflection that updates memory tree nodes, to propagate new insights upward through the tree hierarchy. After EVERY reflection, update the memory tree to propagate new insights upward.
Step 0: Load Conventions
Step 0: Load Conventions — Bash: load-conventions.sh with each name from the conventions: front matter. Read only the paths returned (files not yet in context). If output is empty, all conventions already loaded — proceed to next step.
Step 1: Identify Affected Node (Dynamic Lookup)
Use dynamic lookup to find the right node — never hardcode category->path:
node=$(bash core/scripts/tree-find-node.sh --text "{hypothesis.category}" --leaf-only --top 1)
# Returns: {key, score, file, depth, summary, node_type}
target_file = node.file
Also update performance nodes as needed:
- Pattern/violation discovery →
bash core/scripts/tree-find-node.sh --text "pattern-extraction" --top 1 - Calibration insight →
bash core/scripts/tree-find-node.sh --text "calibration-analysis" --top 1 - Accuracy change →
bash core/scripts/tree-find-node.sh --text "hypothesis-accuracy" --top 1
Step 2: Update Target Node (Depth-Generic)
Behavior depends on whether the target node is a leaf or interior node:
If target is a LEAF node AND insight is substantial (>1 sentence) AND depth < D_max (20):
- Create a NEW child .md file under the leaf's directory
- Register child and convert former leaf to interior:
echo '{"key":"","summary":""}' | bash core/scripts/tree-update.sh --add-child --encoding-source reflect-tree-update
--encoding-source attributes the new child to the Shared Tree Update Protocol
in meta/l1-pick-log.jsonl (S9). Auto-logging fires regardless; this enriches
the entry. Pass --encoding-reason "" when there's a 1-line
semantic justification worth capturing.
The add-child enforces a pre-create dedup gate (Phase 2 curation).
On exit 3 (summary overlap with an existing sibling under the new parent),
read the rejected JSON from stderr for
sibling_keyand UPDATE that siblingin place with the new insight — do NOT retry with a different key.
Exit 2 (exact key match) signals the new-child name collides with a sibling.
bash core/scripts/tree-update.sh --set node_type interior - Move the original leaf content into a child if needed, then add the new child
- Invoke
/tree validateto check the structural change
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.
- 9d ago First seen · 124 lines · 93 tokens per session scan A 7f15bf849188
reflect-tree-update is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 1,778 once invoked, about $0.0005 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 2026-08-31.
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
A skill for working with an Obsidian vault, which is a folder of Markdown notes used as a personal knowledge base. It covers creating, extending, searching, and organizing notes, including links, tags, folders, and daily entries.
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…