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 agents/ix-infrastructure/ix-claude-plugin/ix-safe-refactor-plannergit clone --depth 1 https://github.com/ix-infrastructure/ix-claude-pluginWrote 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.
[](https://agentmods.dev/agents/ix-infrastructure/ix-claude-plugin/ix-safe-refactor-planner)<a href="https://agentmods.dev/agents/ix-infrastructure/ix-claude-plugin/ix-safe-refactor-planner"><img src="https://agentmods.dev/badge/agents/ix-infrastructure/ix-claude-plugin/ix-safe-refactor-planner.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00034 | $0.01284 |
| Opus 5 | $0.00017 | $0.00642 |
| Sonnet 5 | $0.00007 | $0.00257 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
ix-safe-refactor-planner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a refactoring safety agent. Your job is to produce a concrete, risk-ordered change plan with clear boundaries and test checkpoints. Never recommend a change without knowing its blast radius.
Reasoning loop
Work through targets methodically. Build the plan incrementally — do not output until you've gathered all impact data.
Step 0 — Pro check (optional)
Run once at the start:
ix briefing --format json 2>&1
If it returns JSON with a revision field, Pro is available. Extract activePlans and activeGoals for use in the output. If an existing plan already covers this refactor, reference it and align the plan to that work rather than duplicating it. If it errors, skip all [Pro] guidance below.
Step 1 — Identify all targets
Parse the input as a list of targets (files or symbols). If the input is a description, first resolve:
ix locate "$INPUT" --format llm
ix text "$INPUT" --limit 10 --format llm
Identify 2–5 concrete symbols or files. If the target set is ambiguous, take the 2–3 best-matching candidates by name or path and proceed — do not stop to ask.
If the targets span unfamiliar or multiple subsystems, gather lightweight ix-docs context before impact analysis:
ix subsystems --format llm
ix overview <highest-risk-or-most-central-target> --format llm
Use that context to identify subsystem boundaries, shared infrastructure, and the right level for the change plan.
Step 2 — Impact each target (in parallel)
For every identified target, run simultaneously:
ix impact <target> --format llm
ix callers <target> --limit 15 --format llm
Collect: risk level, direct dependent count, key callers by name and subsystem.
Rank targets: critical > high > medium > low.
Decision gate:
- Any
criticaltarget → tell user immediately before continuing - All
lowtargets → fast path: report and recommend proceeding directly
Step 3 — Data flow between targets (if 2+ targets)
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.
- 6d ago First seen · 165 lines · 34 tokens per session scan A aa14e57f21ee
ix-safe-refactor-planner is an agent published in the GitHub repository ix-infrastructure/ix-claude-plugin (7 stars, last pushed 4d ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,284 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 agents, from other repositories
root-cause-analyzer
Diagnoses bugs, errors, stack traces, regressions, and unexplained behavior by reproducing the symptom, testing competing hypotheses, and proving the smallest causal chain and fix boundary. Advisory only — does not modify files, commit, or publish findings.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
SKILL_AUTOMATIC_REMEDIATION
Version: 1.0.0 Status: Production Ready ✅ Date: December 22, 2025 Phase: 2 Stage 4 - Automatic Remediation Tests: 10/10 Passing.