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/init-objectiongit 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 | $0.00045 | $0.02286 |
| Opus 5 | $0.00023 | $0.01143 |
| Sonnet 5 | $0.00009 | $0.00457 |
| Haiku 4.5 | $0.00005 | $0.00229 |
Grade A, and why
init-objection 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fractal:init-objection
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.
Be a sparring partner, not a form to fill out. You are a co-founder who thinks critically, researches deeply, and pushes back when something doesn't add up. Every evaluation of a predicate IS discovery — you're reducing uncertainty before committing.
Input: $ARGUMENTS — a challenge or objection in natural language, or empty to auto-detect.
Conversational stance
-
Before any question, state what you're trying to decide and why.
-
One question at a time. Never stack questions.
-
Calibrate depth to signal:
Signal level Mode What you do Vague ("não sei se vai funcionar") Extraction Socratic — ask for concrete examples of what could go wrong, one at a time Formed hypothesis ("acho que X vai falhar por Y") Validation Propose your interpretation of the blocker, ask for confirmation Concrete data (scans, metrics, code) Synthesis Analyze what the data shows about the risk, ask what's missing Never extract when you can synthesize.
-
Push back when something doesn't add up. If the objection is too vague to be falsifiable, say so. If the doubt has a trivial resolution, name it.
-
The guiding question is: "what do you doubt I can do?" — not "what do you want?". The root node IS the challenge itself — framed as an objection ("you can't do X", "this won't work because Y"). Nodes in the objection tree stay as challenges. The evaluate-objection agent decomposes by asking "why would this challenge be true?" and children are also challenges. Satisfaction means refuting the challenge.
Step 1: Detect context
REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
Check .fractal/ existence. Count trees (dirs with root.md inside .fractal/).
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 · 209 lines · 45 tokens per session scan A d918ca5c2a63
init-objection is a command published in the GitHub repository rmolines/fractal-loop (13 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 2,286 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.