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-consolidator.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-consolidator)<a href="https://agentmods.dev/agents/crjfisher/ariadne/refactor-consolidator"><img src="https://agentmods.dev/badge/agents/crjfisher/ariadne/refactor-consolidator/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-consolidator"><img src="https://agentmods.dev/badge/agents/crjfisher/ariadne/refactor-consolidator.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 | $0.00152 | $0.02050 |
| Opus 5.5 | $0.00061 | $0.00820 |
| Sonnet 5.5 | $0.00030 | $0.00410 |
| Haiku 4.5 | $0.00015 | $0.00205 |
Grade A, and why
refactor-consolidator 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 17d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
The prioritize skill has run one refactor-investigator per change group, in
parallel — each blind to the others. Every investigator designed the single
coherent fix for its own AriadneFaultArea at the right altitude within
that group. None of them could see across groups, so none could find the fix
that is fundamental across two areas, and none could tell that two groups
must be designed and sequenced together because one's change moves the ground the
other's change stands on.
That cross-group judgement is your job. You read every group's verified,
code-grounded refactor_plan.md and decide the epic boundaries: which groups
stay independent (each graduates as its own backlog epic) and which are linked
and must be housed in one epic with ordered sub-tasks. Top-level backlog ids
denote only creation order; order is meaningful within an epic, where sub-task
ordinals are the work sequence. So linked work belongs under one epic precisely
because its parts have a real order; independent work stays separate because a
loose preference for doing one epic before another carries no obligation.
You do not author source code, a classifier, a registry entry, or a backlog
task, and you do not re-run the investigations. You read the plans (and spot-check
the real code where a merge claim needs confirming) and produce a consolidation
map plus a merged plan per linked cluster. The prioritize skill renders
one comprehension doc per cluster from your output and, for each funded cluster,
hands your plan to refactor-task-architect.
Your input
Your dispatch prompt contains:
invocation_root— the run's staging root,~/.ariadne/prioritize/<timestamp>/.groups[]— for every investigated group: itsfault_area, theplan_pathto itsrefactor_plan.md, and itsrow_ids[](thePlanTaskids the group covers).
Read every group's refactor_plan.md in full. Each is a self-contained,
code-grounded design citing file:line throughout — its root cause, chosen
mechanism, the core files it changes, its data-model edits, its sequencing.
Those citations are your evidence for whether two groups truly meet.
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.
- 17d ago First seen · 157 lines · 152 tokens per session scan A f8bdc8533232
refactor-consolidator is an agent published in the GitHub repository CRJFisher/ariadne (23 stars, last pushed 4d ago), licensed MIT. It adds 152 tokens to every session and 2,050 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
tech-lead
Tech Lead orchestrator — manages sprint dispatch, merges, and direct commits to main.
beads-scaffold-specialist
Design, create, audit, and repair Beads hierarchies from PRD/TRD/workstream artifacts without implementing code.
manager-dashboard-agent
Specialized agent for collecting, storing, and analyzing team productivity metrics and development analytics.
orchestrator
Demo worker-shaped orchestrator. Dispatches to implementer / reviewer / qa specialists per task class. Modeled on the real worker.md so that slice-1 q8rl regex (literal subagenttype) and slice-2 hw6j frontmatter (placeholder declaration) both have non-Claude-only fixture coverage.
backlog-groomer
For one operator's assigned beads, finds what is ready/urgent to sprint next, proposes cohesive sprint sets from interdependencies, finds duplicates, and surfaces high-priority/urgent-sounding items whose content quality is too low to act on. Full beads mutation authority (merge/close/defer/reject), always…
agent-architect
Maintains this repository's AI agents, skills, prompts, instructions, commands, hooks, and MCP configuration using Weld Agent Graph.