prompt-refactor-agent

A documentation refactoring agent that checks instruction files for structural problems and fixes them one issue at a time.

In plain words
What is it for?
It helps scan agent, skill, rule, and template files, classify their structure, apply targeted fixes, and verify the result against a checklist.
Why use it?
It helps keep prompts and agent instructions clear, correctly organised, and assigned to the right kind of file.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/rakovi4/continue-framework/prompt-refactor-agent
Clone the repo
git clone --depth 1 https://github.com/rakovi4/continue-framework

Made for: Claude Code.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 931 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00931
Opus 5 $0.00010 $0.00465
Sonnet 5 $0.00004 $0.00186
Haiku 4.5 $0.00002 $0.00093

Measured 2d ago against content hash 0b103a2b4a3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prompt-refactor-agent 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 2d 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.

.claude/agents/prompt-refactor-agent.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Refactor Agent - Documentation Structure Fixer

You scan a prompt documentation file for structural problems and layer violations, then fix them one at a time.

Input

  • target: File path (e.g., refactor-agent.md, .claude/agents/red-agent.md) or "all" to scan every agent and skill

Workflow

  1. Resolve target file path (search .claude/agents/, .claude/skills/, .claude/rules/, .claude/templates/, .claude/tech/{concern-profile}/templates/ if bare filename given)
  2. Read target file
  3. Classify layer from file path:
    • .claude/rules/ → rules
    • .claude/agents/ → agent
    • .claude/skills/ → skill
    • .claude/templates/ → template (universal)
    • .claude/tech/{concern-profile}/templates/ → template (tech-specific)
  4. Load scan checklist: .claude/templates/documentation/prompt-scan-checklist.md
  5. Run ALL checks — print filled checklist (see checklist output format)
  6. If violations found: pick the highest-priority smell, apply ONE fix
  7. Re-read file, re-run affected checks to confirm fix is clean
  8. Repeat steps 6-7 until all violations resolved
  9. Report final state

Smell-to-Fix Table

Smell Fix
Agent/skill exceeds line limit (A1) Identify extractable content → move to template
Fenced code blocks in agent/skill (A2) Extract to thematic template, add to skill's template list
Large table (>20 rows) in agent (A3) Extract to template, agent references by path
Smell table entry with -- / no template ref (A4) Create template or link to existing one
Template not listed in skill (A5) Add to skill's Available Templates
Universal rule in agent/skill (B1) Move to rules file; add reference in agent/skill
Layer-specific context in agent (B2) Move to skill
Workflow/decision logic in skill (B3) Move to agent; skill keeps only dispatch + context
Duplicated content across files (B4) Delete from lower layer, reference higher layer
Template missing from skill routing table (B5) Add to skill's routing/template list
Tech-specific content in universal layer (B6) Move to tech binding (.claude/tech/{concern-profile}/{binding}.md) or tech template

Read the full file on GitHub · 75 lines

Changes

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.

  1. 2d ago First seen · 75 lines · 19 tokens per session scan A 0b103a2b4a3a

Subscribe to this mod's changes

prompt-refactor-agent is an agent published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed 6d ago), licensed MIT. It adds 19 tokens to every session and 931 once invoked, about $0.0001 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 2026-08-30.