tree-review

A read-only review command for checking the structure of a project’s “fractal tree,” where branches represent organized areas of work or decisions.

In plain words
What is it for?
Use it to inspect the full tree, review branch relationships, suggest restructuring, and audit the quality of the conditions that define each branch.
Why use it?
It helps find missing coverage, overlapping branches, uneven structure, outdated branches, and weak conditions before the tree becomes harder to maintain.

Command

Part of the fractal plugin — 15 commands, 4 agents shipped together

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 commands/rmolines/fractal-loop/tree-review
Clone the repo
git clone --depth 1 https://github.com/rmolines/fractal-loop

Or install fractal, the plugin that ships this one along with the rest of its 15 commands, 4 agents.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 837 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00021 $0.00837
Opus 5 $0.00010 $0.00418
Sonnet 5 $0.00004 $0.00167
Haiku 4.5 $0.00002 $0.00084

Measured 2d ago against content hash b729c444d6c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tree-review 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.

commands/tree-review.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/fractal:tree-review

Human gates

Every time this skill needs human input (confirmation, choice, correction), use the AskUserQuestion tool instead of printing the question as text output. This ensures the agent pauses and waits for the response before continuing.

You are a strategic advisor reviewing the fractal tree structure. Your goal is to surface misalignments, stale branches, predicate quality issues, and suggest restructuring.

This skill is read-only. It never modifies the tree.


On entry

1. Load full tree

REPO_ROOT=$(git rev-parse --show-toplevel)
FRACTAL_SCRIPTS=$(ls -d ~/.claude/plugins/cache/fractal/fractal/*/scripts 2>/dev/null | tail -1)
bash "$FRACTAL_SCRIPTS/fractal-tree.sh"
bash "$FRACTAL_SCRIPTS/fractal-state.sh"

Read root.md and ALL predicate.md files in the tree. Read discovery.md where it exists. Read learnings.md if present.

2. Structural analysis

For each branch node, assess:

  • Coverage: Do the children collectively cover the parent predicate? Are there gaps?
  • Overlap: Do any siblings overlap in scope? Could they be merged?
  • Depth balance: Are some branches much deeper than others? Does the depth reflect genuine complexity or over-decomposition?
  • Stale nodes: Any candidate nodes that have been sitting unattended? Any pending nodes whose parent context has changed?

3. Predicate quality audit

For each predicate, check:

  • Falsifiability: Can you clearly say yes/no to this predicate? Or is it vague?
  • Functional vs technical: Are technical predicates exposed at leaf level where humans validate? (See LAW.md "Predicate formulation" section)
  • Scope fit: Is the predicate at the right level of abstraction for its depth? Too broad for a leaf? Too narrow for a branch?
  • Alignment with root: Does this predicate contribute to the root objective? Or has it drifted?

4. Realignment suggestions

Based on the analysis, propose concrete actions. Group by type:

Read the full file on GitHub · 101 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 · 101 lines · 21 tokens per session scan A b729c444d6c3

Subscribe to this mod's changes

tree-review is a command published in the GitHub repository rmolines/fractal-loop (13 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 837 once invoked, about $0.0001 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.