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.
npx skills add slash9494/ai-config-sync-manager --skill config-manager-paraphrasegit clone --depth 1 https://github.com/slash9494/ai-config-sync-managerWrote 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/skills/slash9494/ai-config-sync-manager/config-manager-paraphrase)<a href="https://agentmods.dev/skills/slash9494/ai-config-sync-manager/config-manager-paraphrase"><img src="https://agentmods.dev/badge/skills/slash9494/ai-config-sync-manager/config-manager-paraphrase/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/skills/slash9494/ai-config-sync-manager/config-manager-paraphrase"><img src="https://agentmods.dev/badge/skills/slash9494/ai-config-sync-manager/config-manager-paraphrase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.01217 |
| Opus 5 | $0.00026 | $0.00609 |
| Sonnet 5 | $0.00011 | $0.00243 |
| Haiku 4.5 | $0.00005 | $0.00122 |
Grade A, and why
config-manager-paraphrase scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Config Manager Paraphrase
Use this skill when the user asks to paraphrase host-strict vocabulary mismatches, register manual-review overrides, or pre-register lines that were already paraphrased outside the CLI.
Behavior
- If the user passes
-h/--help(or asks for usage/help), run... paraphrase --helpand print the CLI output as-is — do not run a dry-run, register, or apply. - Resolve the bundled CLI from the Codex plugin root:
AI_CONFIG_SYNC_HOST=codex "$HOME/.agents/plugins/ai-config-sync-manager/bin/ai-config-sync" paraphrase. The launcher resolves the runtime viaAI_CONFIG_SYNC_ROOT(dev override) → PATHai-config-sync→npm execfallback. - Always export
AI_CONFIG_SYNC_HOST=codexbefore invoking the CLI from this skill so the default sync direction iscodex -> claude. Paraphrase processes both directions regardless: claude-only tokens in codex files become codex-side paraphrases, and codex-only tokens in claude files become claude-side paraphrases. - Default mode is dry-run preview. Apply only after the user explicitly confirms in chat.
- Default scope is global+project unless the user passes
--scope global,--scope project, or--scope all. - For partial paraphrase, pass selectors with
--include area[:item][,...]and--exclude area[:item][,...]. Item selectors are supported for itemized areas such asagents,skills, andinstructions. - Print the CLI output as-is. Do not rewrite or summarize the dry-run report into a different format.
- The CLI registers each rewritten line in
rules/paraphrase-overrides.json. Verify the entries match the planned changes before applying. - If the bundled CLI is unavailable, report that the user must
npm install -g ai-config-sync-manager(or runnpm linkfrom the repo) and re-runconnect.
Natural-Language Intent → CLI Flag Mapping
If the user gives natural-language intent (Korean or English) instead of CLI flags, translate it to flags before running:
"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 bundledrules/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
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.
- 11d ago First seen · 65 lines · 53 tokens per session scan A 7a56ac58b18e
config-manager-paraphrase is a skill published in the GitHub repository slash9494/ai-config-sync-manager (38 stars, last pushed 6d ago), licensed MIT. It adds 53 tokens to every session and 1,217 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…