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/proposegit 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 | $0.00043 | $0.04111 |
| Opus 5 | $0.00022 | $0.02056 |
| Sonnet 5 | $0.00009 | $0.00822 |
| Haiku 4.5 | $0.00004 | $0.00411 |
Grade A, and why
propose 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 today.
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 — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fractal:propose
Human gates
Every time this skill needs human input, use the AskUserQuestion tool instead of printing the question as text output.
Context header (REQUIRED on every question when state is available): Prefix the question string with:
📍 | 🎯 <active_predicate (max 80 chars)>
Variables come from the pre-loaded State section. If state is not yet loaded (e.g., early steps before tree detection), omit the header.
IMPORTANT: The header must be plain text. No markdown formatting (no **, ##, *, etc.) in the question string. Emojis are fine as visual anchors.
Input: $ARGUMENTS — predicate text in natural language, or empty to enter analyze mode.
Step 1: Route on arguments
If $ARGUMENTS IS provided
Use it directly as the predicate text. Skip to Step 2 (Reframe).
If $ARGUMENTS is empty — ANALYZE MODE
Enter analyze mode. This evaluates the active predicate and proposes the next sub-predicate.
Step A: Detect tree
REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
FRACTAL_DIR="$REPO_ROOT/.fractal"
TREES=()
for d in "$FRACTAL_DIR"/*/; do [ -f "${d}root.md" ] && TREES+=("$d"); done
if [ "${#TREES[@]}" -eq 1 ]; then
TREE_DIR="${TREES[0]}"
elif [ "${#TREES[@]}" -gt 1 ]; then
# Multiple trees — ask user which to use via AskUserQuestion
echo "multiple_trees: true"
for t in "${TREES[@]}"; do echo "tree: $(basename "$t")"; done
fi
If no tree found: STOP with message "Nenhuma árvore fractal encontrada. Execute /fractal:init primeiro."
If multiple trees found: ask the user which tree to work with via AskUserQuestion.
ROOT_MD="${TREE_DIR}root.md"
ACTIVE_NODE=$(grep "^active_node:" "$ROOT_MD" | sed 's/^active_node:[[:space:]]*//' | tr -d '"')
FRACTAL_SCRIPTS=$(ls -d ~/.claude/plugins/cache/fractal/fractal/*/scripts 2>/dev/null | tail -1)
[ -z "$FRACTAL_SCRIPTS" ] && FRACTAL_SCRIPTS="$REPO_ROOT/scripts"
bash "$FRACTAL_SCRIPTS/fractal-state.sh"
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.
- today First seen · 461 lines · 43 tokens per session scan A 06a9f2089d38
propose is a command published in the GitHub repository rmolines/fractal-loop (13 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 4,111 once invoked, about $0.0002 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-arch
Scan project structure and generate Mermaid architecture diagrams + flowcharts under .pm/architecture/.
pm-done
Close a todo (TODO-xxx), sync completed.md, refresh overview.
pm-status
Show governance health, wizard next step, all open blocking/high todos, and pending review count. Primary daily entry.
pm-charter
Create, import, discover, approve, or skip project charter. No-arg form is an interactive wizard.
_closing
会改 .pm/ 的 /pm- 回复必须有一句中文摘要。链接只列已经存在的文件,不要指向还没生成的路径。.
pm-tests
List missing unit-test companions for core/changed sources. Do not write tests into the business tree unless the user confirms.