A validator for fractal trees, which are structured folders of predicates and related work. It checks the tree for missing or inconsistent information and can optionally offer fixes.

Use it to inspect fractal trees in read-only mode or interactively repair reported inconsistencies with the fix option.

It finds structural problems before they cause later planning or execution steps to fail.

doctor — Command for Claude Code by rmolines/fractal-loop

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.

Clone the repo

git clone --depth 1 https://github.com/rmolines/fractal-loop

Made for: Claude Code.

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

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/rmolines/fractal-loop/doctor/github.svg)](https://agentmods.dev/commands/rmolines/fractal-loop/doctor)

Your own site

<a href="https://agentmods.dev/commands/rmolines/fractal-loop/doctor"><img src="https://agentmods.dev/badge/commands/rmolines/fractal-loop/doctor/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/rmolines/fractal-loop/doctor"><img src="https://agentmods.dev/badge/commands/rmolines/fractal-loop/doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,225 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00012	$0.01225
Opus 5.5	$0.00005	$0.00490
Sonnet 5.5	$0.00002	$0.00245
Haiku 4.5	$0.00001	$0.00122

Measured 1mo ago against content hash 7d6cfd08e2cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

doctor 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 1mo 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/doctor.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/fractal:doctor

Human gates

Every time this skill needs human input (confirmation, choice, correction), use the AskUserQuestion tool instead of printing the question as text output.

Input: $ARGUMENTS — pass --fix to enable interactive cleanup mode.

Mode

Default: read-only validation. Reports issues, changes nothing.
--fix: interactive cleanup. Asks for confirmation via AskUserQuestion before each fix.

On entry

REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
FRACTAL_DIR="$REPO_ROOT/.fractal"

If .fractal/ does not exist → "Nenhuma árvore encontrada. Execute /fractal:init." STOP.

Checks — execute in order

Check 1: Tree presence

Count top-level dirs with root.md inside .fractal/.

0 trees → [FAIL] Nenhuma árvore encontrada.
1 tree → [PASS] Uma árvore: <name>
N > 1 → [INFO] Múltiplas árvores: <list>. Validate each tree independently.
- --fix: offer to archive trees where root status is satisfied.

Check 2: root.md integrity

Read .fractal/<tree>/root.md. Validate frontmatter:

predicate exists and is non-empty
status is a valid value (pending | satisfied | pruned)
active_node exists
created exists

Each missing/invalid field: [FAIL] root.md: campo '<field>' ausente ou invalido.

--fix for active_node: reset to .
--fix for status: set to pending

Check 3: active_node pointer

If active_node != .:

Check that .fractal/<tree>/<active_node>/ directory exists
Check that .fractal/<tree>/<active_node>/predicate.md exists

If broken: [FAIL] active_node aponta para diretorio inexistente: <path>

--fix: reset active_node to . in root.md

Check 4: predicate.md files

For every directory inside the tree (recursive), check:

predicate.md exists (dirs without it are orphans)
Frontmatter has predicate (non-empty)
status is valid (pending | satisfied | pruned)
created exists

Orphan dirs: [WARN] Diretorio orfao (sem predicate.md): <path>

--fix: ask to remove

Read the full file on GitHub · 142 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.

1mo ago First seen · 142 lines · 12 tokens per session scan A 7d6cfd08e2cb

Subscribe to this mod's changes

doctor is a command published in the GitHub repository rmolines/fractal-loop (14 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 1,225 once invoked, about $0.0000 per session on Opus 5.5. 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.

Claude Code Debugging Project Management ai-agents anthropic claude plugin

doctor