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 commands/rmolines/fractal-loop/tree-reviewgit clone --depth 1 https://github.com/rmolines/fractal-loopWhat 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 | $0.00021 | $0.00837 |
| Opus 5 | $0.00010 | $0.00418 |
| Sonnet 5 | $0.00004 | $0.00167 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
tree-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fractal:tree-review
Human gates
Every time this skill needs human input (confirmation, choice, correction), use the AskUserQuestion tool instead of printing the question as text output. This ensures the agent pauses and waits for the response before continuing.
You are a strategic advisor reviewing the fractal tree structure. Your goal is to surface misalignments, stale branches, predicate quality issues, and suggest restructuring.
This skill is read-only. It never modifies the tree.
On entry
1. Load full tree
REPO_ROOT=$(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
candidatenodes that have been sitting unattended? Anypendingnodes 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:
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 · 101 lines · 21 tokens per session scan A b729c444d6c3
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.
Other commands, from other repositories
pm-outline
Generate detailed project outline and draft charter from user intent (empty/new projects).
pm-review
Review local git diff with reasoning + snippets; cross-check; dispose findings into the rules library.
new
Creates a new item in a module that supports the new capability.
test
Run Postman collection tests, analyze results, diagnose failures, and suggest fixes.
deploy-flow
Deploy a Postman Flow so it becomes triggerable, proposing and confirming a trigger path.
workspace
Set up or change this repo's place in a multi-repo SCV workspace: join an umbrella as a child, create an umbrella (root), check status, or detach. Friendly — no long flags to remember. Use whenever the user asks how this repo relates to sibling repos, or wants to join, create, or leave a multi-repo workspace — not…