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 agentmods add skills/recca0120/code-quest/protocol-alignmentnpx skills add recca0120/code-quest --skill protocol-alignmentgit clone --depth 1 https://github.com/recca0120/code-questWhat 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 | $0.00041 | $0.01116 |
| Opus 5 | $0.00020 | $0.00558 |
| Sonnet 5 | $0.00008 | $0.00223 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
protocol-alignment 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Protocol Alignment — cc-office vs Claude Code Extension
This skill only does protocol comparison. Finding gaps is the job here.
Implementation is a separate concern — open a change with /opsx:new after comparison.
Extension Reference
/Users/user/Desktop/anthropic.claude-code-2.1.45-darwin-arm64/
└── src/core/main.js ← 主要參考（~70k 行，webcrack + prettier）
Read references/extension-surface.md for the extracted protocol surface.
When the extension updates, re-extract and diff against that file.
Protocol 只在 3 個檔案
apps/summoner/src/protocol/
├── claude-schemas.ts ← CLI 送什麼給我們（event type Zod schemas + type registry）
├── claude.ts ← 我們送什麼給 CLI（LaunchOptions + buildArgs + parseLine + format methods）
└── claude-adapter.ts ← ProtocolEvent → SocketEvent 純轉換（event type 路由 + control_request dispatch）
比對 extension 時只看這 3 個檔案。其他都是應用層，不是 protocol。
claude-adapter.ts 也定義 clientConfig: ProviderClientConfig（brand、permissionModes、authMethods、mcpScopes、usageTiers、modelDisplayMap）。
Client 透過 get_provider_config socket event 取得，存在 ChannelConfigContext。
怎麼比對
1. 提取 extension protocol surface
Read references/extension-surface.md。如果 extension 更新了，重新提取：
grep -n 'subtype.*"' src/core/main.js # all subtypes
grep -n '\.type ===' src/core/main.js # event type routing
搜尋這些區域（用函數名，不用行號）：
- readMessages: event type 路由
- processControlRequest: 收到的 control_request subtype
- this.request(: 發送的 control_request subtype
- CLI arg building: spawn 時的 argv
2. 對照 cc-office 3 個檔案
| 比對項目 | 查哪個檔案 | 搜尋 pattern |
|---|---|---|
| event type 有沒有 schema | claude-schemas.ts |
z.literal('typename') |
| event type 有沒有轉換成 ClientEvent | claude-adapter.ts |
event.type === 'typename' |
| control_request subtype（收到的） | claude-adapter.ts |
case 'subtypename' in convertControlRequest |
| control_request subtype（發送的） | 不需查（formatControlRequest 是 generic 的，任何 subtype 都能發） |
|
| CLI spawn arg | claude.ts |
LaunchOptions + buildArgs() |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 108 lines · 41 tokens per session scan A bd57ce5baadd
protocol-alignment is a skill published in the GitHub repository recca0120/code-quest (11 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 1,116 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…