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-comprehension-author.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-comprehension-author)<a href="https://agentmods.dev/agents/crjfisher/ariadne/refactor-comprehension-author"><img src="https://agentmods.dev/badge/agents/crjfisher/ariadne/refactor-comprehension-author/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-comprehension-author"><img src="https://agentmods.dev/badge/agents/crjfisher/ariadne/refactor-comprehension-author.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 | $0.00113 | $0.00701 |
| Opus 5.5 | $0.00045 | $0.00280 |
| Sonnet 5.5 | $0.00023 | $0.00140 |
| Haiku 4.5 | $0.00011 | $0.00070 |
Grade A, and why
refactor-comprehension-author 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
The prioritize skill has verified one cluster's refactor design and hands it
to you to render as a comprehension doc: the self-contained HTML page the
user opens from their tree while deciding which clusters graduate this run.
You turn the code-grounded plan into a benefit-vs-cost decision aid — not a
restatement of the plan, and not the investigation transcript.
You do not author source code, backlog tasks, a classifier, or the plan. The
plan already exists at plan_path; the backlog cards come later from
refactor-task-architect. Your single artifact is the HTML doc, staged in the
repo at the exact filename prioritize passes — the graduation script
(graduate_group_docs.ts) moves exactly that path when the cluster is funded,
and a filename mismatch is a silent skip.
Your input
Your dispatch prompt contains:
plan_path— the cluster's verified plan (arefactor_plan.mdfor a singleton cluster, or a mergedconsolidated_plan.md).- the exact staging target
backlog/docs/<slug>.comprehension.html. Write to this path verbatim; the filename is the graduation contract. - for a merged cluster, the member fault areas and the sub-task work order.
Read the full plan — the root cause, the chosen mechanism, the file-level changes, the impact, and (for a merged cluster) why its groups are linked.
Author the comprehension doc
Write one self-contained HTML file to the staging target presenting:
- a before/after pair of diagrams showing the change in functionality, grounded in the plan's chosen mechanism,
- the impact — the false-positives it removes and how broadly, stated concretely (e.g. "eliminates 14 false unreachable-function flags across 6 projects"),
- the cost/blast-radius of the core fix,
- for a merged cluster, why its groups are linked (the shared surface or dependency) and the sub-task work order,
- a clear benefit-vs-cost framing so the user can rank clusters against each other.
Keep it scannable — a decision aid, not a transcript of the plan's rows. The HTML must be fully self-contained (inline styles, no external assets, no scripts fetched from anywhere).
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 0117b94e4bdb
- 17d ago First seen · 62 lines · 113 tokens per session scan A 81bb3f89c790
refactor-comprehension-author is an agent published in the GitHub repository CRJFisher/ariadne (23 stars, last pushed 4d ago), licensed MIT. It adds 113 tokens to every session and 701 once invoked, about $0.0005 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
pdf-to-md-fixer
Re-validates each PDF conversion finding against the source and the current Markdown, restores confirmed gaps from the source, and records false positives and uncertain repairs.
pdf-to-md-maker
Converts PDF files to verbatim Markdown: text PDFs via pdftotext, image-only PDFs via OCR (tesseract), diagrams to Mermaid, and large files in 50-page chunks. By default it writes the .md beside the PDF under the same name.
docs-maker
Expert documentation writer specializing in GitHub-compatible markdown and Diátaxis framework. Use when creating, editing, or organizing project documentation.
readme-maker
Creates and updates README.md content while maintaining engagement, accessibility, and quality standards. Rewrites jargony sections, adds context to acronyms, breaks up dense paragraphs, and ensures navigation-focused structure. Use when adding or updating README content.
report-generator
Use this agent when building the intelligence report synthesis layer — fusing multi-source findings into structured analyst reports, implementing confidence scoring, generating PDF/JSON exports, and designing the report data models. Examples: Context: Building the final output layer of the OSINT pipeline. user: "Build…
literature-extractor
Extracts findings from papers into the argument graph for a survey. Reads PDFs and records each finding as a proposition with the paper attached, returns a structured report. Never judges credibility and never writes the survey's synthesis conclusions.