paraphrase

paraphrase is a command for Claude Code from slash9494/ai-config-sync-manager. It costs 41 tokens per session (690 once invoked), scanned A, original, MIT.

A command for replacing restricted vocabulary in agent and skill files while recording approved line-specific exceptions. It can also translate plain-language requests into the command’s options.

In plain words
What is it for?
Use it to replace specified words, apply the standard replacement rules, limit changes to selected agents or skills, preview edits, or register exceptions without changing the files.
Why use it?
It helps make files acceptable to different host tools while preserving a record of intentional wording changes for future checks.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the config-manager plugin — 1 skill, 5 commands shipped together

Good fit Use it to replace specified words, apply the standard replacement rules, limit changes to selected agents or skills, preview edits, or register exceptions without changing the files.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add slash9494/ai-config-sync-manager
Claude Code
/plugin install config-manager

Made for: Claude Code.

Or install config-manager, the plugin that ships this one along with the rest of its 1 skill, 5 commands.

Wrote 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.

agentmods badge for paraphrase

README.md
[![agentmods](https://agentmods.dev/badge/commands/slash9494/ai-config-sync-manager/paraphrase.svg)](https://agentmods.dev/commands/slash9494/ai-config-sync-manager/paraphrase)
Your own site
<a href="https://agentmods.dev/commands/slash9494/ai-config-sync-manager/paraphrase"><img src="https://agentmods.dev/badge/commands/slash9494/ai-config-sync-manager/paraphrase.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 690 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00041 $0.00690
Opus 5 $0.00020 $0.00345
Sonnet 5 $0.00008 $0.00138
Haiku 4.5 $0.00004 $0.00069

Measured 8d ago against content hash 5274927ca664, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

paraphrase 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 8d 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.

integrations/claude-plugin/commands/paraphrase.md · 36 lines

What it actually says

If $ARGUMENTS is natural-language intent (Korean or English) instead of CLI flags, translate it into the matching paraphrase CLI flags before running. Mapping rules:

  • "X를 Y로 치환" / "X to Y"--map "X=Y" (multiple mappings comma-separated: --map "Read=Inspect,Write=Emit")
  • "codex에서 실행가능한 단어로 치환" / "host-strict 자동 치환" / "일반 paraphrase" → no --map (uses bundled rules/paraphrase-map.json)
  • explicit agent/skill scope (e.g. "repo-code-analyst만") → --include agents:<name> or --include skills:<name>
  • "등록만" / "등록해줘" / "register only" / "파일은 그대로 두고 override만" / "이미 치환된 라인" / "pre-paraphrased" / "수동으로 치환된"--register (skip the rewrite stage, append override entries directly when the effective map equates the diverging line pair)
  • Arguments that already start with -- → passed through as-is

First run a dry-run preview (paraphrase defaults to dry-run unless --apply is given). When $ARGUMENTS looks like CLI flags or is empty, the CLI runs immediately; when it looks like natural-language intent, the bash branch prints a notice and you should translate it to flags using the mapping rules above, then re-invoke with the explicit flags:

!AI_CONFIG_SYNC_HOST=claude bash -lc 'case "$ARGUMENTS" in ""|--*) "${CLAUDE_PLUGIN_ROOT}/bin/ai-config-sync" paraphrase '"$ARGUMENTS"' ;; *) echo "[natural-language intent detected] $ARGUMENTS — translate to paraphrase CLI flags using the mapping rules above, then run the bash command at the bottom of this skill." ;; esac'

Confirmation flow:

  • The slash command always shows a dry-run preview first.
  • After reviewing the preview, ask the user in chat whether to apply.
  • On the user's explicit yes, re-run this command with --apply appended.

Before applying changes:

  • Summarize the CLI output exactly; show which files and lines will be rewritten.
  • Highlight tokens that have no paraphrase yet (CLI labels them pendingTokens) and ask the user for explicit mappings before applying.
  • The CLI registers each rewritten line in rules/paraphrase-overrides.json; verify the entries match the planned changes.

Apply only after the user explicitly confirms in chat:

AI_CONFIG_SYNC_HOST=claude "${CLAUDE_PLUGIN_ROOT}/bin/ai-config-sync" paraphrase $ARGUMENTS --apply
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. 8d ago First seen · 36 lines · 41 tokens per session scan A 5274927ca664

Subscribe to this mod's changes

paraphrase is a command published in the GitHub repository slash9494/ai-config-sync-manager (36 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 690 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 2026-08-30.