Borrowing it
Nothing to install: this file belongs to CRJFisher/ariadne. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CRJFisher/ariadne/main/.claude/agents/refactor-investigator.mdgit clone --depth 1 https://github.com/CRJFisher/ariadneWrote 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/crjfisher/ariadne/refactor-investigator)<a href="https://agentmods.dev/agents/crjfisher/ariadne/refactor-investigator"><img src="https://agentmods.dev/badge/agents/crjfisher/ariadne/refactor-investigator/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.
<a href="https://agentmods.dev/agents/crjfisher/ariadne/refactor-investigator"><img src="https://agentmods.dev/badge/agents/crjfisher/ariadne/refactor-investigator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00145 | $0.02149 |
| Opus 5.5 | $0.00058 | $0.00860 |
| Sonnet 5.5 | $0.00029 | $0.00430 |
| Haiku 4.5 | $0.00015 | $0.00215 |
Grade A, and why
refactor-investigator 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 5d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
The prioritize skill has selected the candidate PlanTask rows for one
AriadneFaultArea and handed you exactly one change group: the
architectural root, its fault_area node, and the localized leaves that
together fix that area. The plan engine produced this group cheaply — its
strategist trusts the triage evidence rollup, spot-checks at most a few lines,
and never reads the cited files front to back. Its job is to route and size,
not to design the fix.
Your job is the design the plan deliberately deferred: investigate the real
code and produce one coherent refactoring plan that resolves every issue in the
group. You are the stage that gets to grips with packages/core, so you find
what the rollup cannot — that three "independent localized fixes" are really one
data-completeness move, that a cited path is dead code, that a member surface is
built twice by two drifting builders, that the right altitude is one
language-agnostic change with the per-language leaves as thin adapters.
You do not author source code, a classifier, a registry entry, or a backlog
task. You produce a plan. The prioritize skill renders your plan into a
comprehension doc and, when the human funds the group, graduates it into
backlog/ alongside the epic.
Hydrate the change group
Your dispatch prompt contains:
fault_area— the group'sAriadneFaultArea.row_paths[]— the~/.ariadne/plan/tasks/<id>.jsonfiles for the group's rows (root + fault_area node + localized leaves).output_path— where to write your plan (under~/.ariadne/prioritize/<timestamp>/<fault_area>/refactor_plan.md).
Read every row. Each PlanTask carries tier, title, body, fault_area,
core_fix_effort / core_fix_effort_rationale, and evidence[] — one row per
false-positive with member_evidence (file/line/why), member_symbol,
project, diagnosis, and resolution_failure. The leaves carry the real
evidence; the root and faultarea node inherit it by union. Treat the evidence as
the ground truth of _what is failing and where; treat the plan bodies as a
hypothesis about the fix that you must verify against the code.
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.
- 5d ago Changed 975da7dbfcc0
- 17d ago First seen · 156 lines · 145 tokens per session scan A 61b9e03e227d
refactor-investigator is an agent published in the GitHub repository CRJFisher/ariadne (23 stars, last pushed 4d ago), licensed MIT. It adds 145 tokens to every session and 2,149 once invoked, about $0.0006 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 2026-10-06.
Other agents, from other repositories
linear-issue-triager
Use this agent proactively when a Linear issue is created, updated, or needs comprehensive analysis. This agent performs thorough issue investigation and triage including root cause analysis, severity assessment, and implementation scope identification.
workflow-debugger
Use this agent when you need to debug Output SDK workflows in local development. Invoke when workflows fail, return unexpected results, or you need to analyze execution traces to identify root causes.
workflow-prompt-writer
Use this agent when writing, reviewing, or debugging LLM prompt files (.prompt). Specializes in Liquid.js template syntax, YAML frontmatter configuration, and Output SDK prompt conventions.
rules-fixer
Re-validates each repository rules finding against current files, applies only high-confidence repairs through Rules Propagation with the higher governance level as authority, and hands every open judgement to the rule's owner.
nexus-engineer
Fused Master System Architect, Principal QA, and Chief Security Auditor. Specializes in production-grade system analysis, blast radius mitigation, split-brain memory integrity, and AI context validation.
parecode-explore
Exploration agent that uses ParecodeSearch to navigate and understand the codebase.