MANDATORY for every coding agent and contributor touching localized content — keep all five localization surfaces (dashboard UI keys, wiki page, full mirrored guides, locale-aware formatting…

MITAuto-check passedFrontend & Design

Install I18n Parity

skills CLI
$ npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill i18n-parity -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hoangsonww/Claude-Code-Agent-Monitor i18n-parity --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hoangsonww/Claude-Code-Agent-Monitor.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/i18n-parity .claude/skills/i18n-parity && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
i18n-parity
GitHub stars
1.1k
Token cost
~3.4k tokens
SKILL.md length
1,617 words
Files
4 (incl. references)
Skills in repo
78
Repo updated
First seen
Licence
MIT

At a glance

MANDATORY for every coding agent and contributor touching localized content — keep all five localization surfaces (dashboard UI keys, wiki page, full mirrored guides, locale-aware formatting…

  • Works in 3 steps: The full-guide mirror must be complete.… → Every app key must be translated. All 15… → The wiki must be translated completely,…
  • Tasks that involve Internationalization
  • SKILL.md covers The five surfaces, Workflow A — you changed…, Workflow B — adding a new… and What stays in English (all…, plus 4 more sections
  • Calls npm, bash and npx

What it does

I18n Parity is an agent skill from hoangsonww/Claude-Code-Agent-Monitor. MANDATORY for every coding agent and contributor touching localized content — keep all five localization surfaces (dashboard UI keys, wiki page, full mirrored guides, locale-aware formatting, language switchers) in parity across every supported language. Use automatically (without being asked) whenever you add or change user-visible UI copy, add an i18n key, edit README-EN.md or a localized guide, edit wiki/index.html, or add a language surface.

Its SKILL.md is about 3.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/new-language-checklist.md` and `references/translation-style.md`).

It sits in Frontend & Design, covering Internationalization. The repository describes itself as: 🚀 A real-time monitoring dashboard for Claude Code & Codex, built with SQLite3, Node.js, Express, React, Vite, TailwindCSS, & WebSockets. It tracks sessions, agent activity… The licence is MIT.

When your agent uses it

  • Tasks that involve Internationalization

Example prompts

  • “/i18n-parity”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. The full-guide mirror must be complete. README-.md is a full mirror of
  2. Every app key must be translated. All 15 namespaces × every key. The
  3. The wiki must be translated completely, not just the headings. That means

What it can do on your machine

Read from SKILL.md and the folder at commit a06db03. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm
    • bash
    • npx
    • claude

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm and npx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

I18n Parity loads about 3.4k tokens when it runs, and up to ~7.6k if it reads all its reference files. Until then it costs about 115 tokens; SKILL.md has 1,617 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~115
When it runs · the whole SKILL.md, loaded when a task matches
~3.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from hoangsonww/Claude-Code-Agent-Monitor at commit a06db03, republished under its MIT licence (© hoangsonww). 1,617 words, ~3,411 tokens.

Download SKILL.mdSave it as .claude/skills/i18n-parity/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
i18n-parity
description
MANDATORY for every coding agent and contributor touching localized content — keep all five localization surfaces (dashboard UI keys, wiki page, full mirrored guides, locale-aware formatting, language switchers) in parity across every supported language. Use automatically (without being asked) whenever you add or change user-visible UI copy, add an i18n key, edit README-EN.md or a localized guide, edit wiki/index.html, or add a language surface.

Mirror. The canonical copy of this skill — and the i18n-audit.sh script it tells you to run — live at .claude/skills/i18n-parity/. Keep the two in sync; edit the canonical copy first.

i18n Parity

This repository is localized on five independent surfaces, each with its own mechanism. A change that lands on one and not the others leaves the product half-translated: the English falls through, and the gap is invisible to anyone working in English. This skill states the invariant, maps every surface to the exact files, and gives one command that proves parity.

The invariant: English is the source of truth on every surface, and no change is done until every supported language carries it in the same PR. A fallback to English is a safety net, never a completed translation.

Supported languages are declared in one place — supportedLngs in client/src/i18n/index.ts. Today: en, zh, vi, ko, es. Everything below derives from that list; the audit script reads it rather than hard-coding.

The five surfaces

#SurfaceEnglish source of truthTranslations live inAutomated gate
1Dashboard UIclient/src/i18n/locales/en/*.jsonclient/src/i18n/locales/<xx>/*.json (same 15 namespaces)client/src/i18n/__tests__/i18n.test.ts — key, type, and interpolation-token parity
2Wiki pageEnglish text in the wiki/index.html DOMwiki/script.js (T, ATTRIBUTE_TRANSLATIONS, META, languageLabels, the two language ladders) + wiki/i18n-content.js (window.__WIKI_CONTENT_I18N, both the body bundles and plain)client/tests/wiki-i18n.test.ts — live-DOM prose coverage, inline-tag preservation, block-length budgets, asset-version sync
3Full mirrored guidesREADME-EN.mdREADME-CN.md (zh), README-VN.md (vi), README-KO.md (ko), README-ES.md (es)partial — scripts/i18n-audit.sh (existence, heading count, cross-links) and server/__tests__/plugins-marketplace.test.js (documented counts); prose parity is review-only
4Language switchers—client/src/components/Sidebar.tsx, client/src/lib/paletteCommands.ts, the two .lang-select-menu blocks in wiki/index.html, nav.json languageNames / languageShortscripts/i18n-audit.sh
5Locale-aware formatting—client/src/lib/format.ts (SupportedLanguage union, getCurrentLanguage() whitelist, getCurrentLocale() BCP-47 map)client/src/lib/__tests__/format.test.ts
What is deliberately NOT localized

Verified against the tree — do not go looking for translation hooks in these, and do not add them without being asked:

  • The root landing page index.html has no i18n layer. Do not add data-lang markup; put localized long-form content in the wiki instead. Its one language-aware element is the Languages (en/zh/…) stat label, which just enumerates the codes.
  • The repository landing page README.md is a concise English-only entry point. It links every complete language guide but is not itself mirrored. Full technical content belongs in README-EN.md and its four translations.
  • client/index.html is an English shell: <html lang="en">, og:locale=en_US, and English <title>/meta. The React app never reassigns document.documentElement.lang when the user switches language — a known gap, not something a translation PR is expected to fix.
  • The CLI (bin/ccam.js + cli/), the MCP server (mcp/), the Express server (server/), the desktop shell (desktop/), the VS Code extension, and the statusline contain no i18n wiring at all. Their output is English.
  • client/src/lib/event-summary.ts and event-grouping.ts build tool-event headlines and bullets from English template literals (Last message: …, 3 lines stdout, 2 matches). Their MODULE_GUIDE boilerplate claims strings belong in i18n JSON, but neither file imports i18next. They sit outside the key system today; do not "fix" them as part of a localization change.
  • Number and date formatting is only locale-aware where the format.ts helpers are used. Most components call toLocaleString() / toLocaleString(undefined, …) directly, which follows the browser locale rather than the chosen UI language. In new code prefer getCurrentLocale() from format.ts; leave existing call sites alone unless asked.

Workflow A — you changed content (the common case)

Find what you touched in the left column and ship everything in the right column in the same PR.

You changedYou must also do
Added/renamed a UI string or i18n keyAdd the key to en and every other locale in the same namespace file. Same key path, same value type, same {{interpolation}} tokens.
Added a new namespace (new *.json)Create it for every locale, then register the imports, the resources entry per language, and the ns array in client/src/i18n/index.ts.
Added user-visible wiki text in wiki/index.htmlFollow .claude/rules/wiki-i18n.md: scannable layer (the PLAIN selector set — .logo-sub, .section-label, .nav-section, .nav-empty, .stat-label, .t-label, h2/h3/h4, th, .hero-desc, plus .nav-link / .hero-badge trailing text nodes) → T in wiki/script.js; body prose (the HTML_SEL set — p, li, td, th, captions, .callout-body > strong, .route-desc, footer) → wiki/i18n-content.js keyed by whitespace-normalized innerHTML; new alt/aria-label/title/placeholder → ATTRIBUTE_TRANSLATIONS. Then bump CACHE_NAME in wiki/sw.js and the matching ?v= query strings.
Edited the English-only landing README.mdKeep it concise and ensure it still links README-EN.md and every localized full guide. Do not copy landing-page prose into the full guides.
Edited a section of README-EN.mdMirror the same edit at the corresponding section of README-CN.md, README-VN.md, README-KO.md, and README-ES.md. All four, every time.
Changed behavior that the README/wiki document (env var, event type, route, CLI command, feature)Run the update-project-docs (.claude/skills/update-project-docs/SKILL.md) skill — it owns the change→docs mapping — then come back here for the translation propagation it triggers.
Changed a documented count (plugins, skills, namespaces, languages)The count can appear in the landing README, all five full guides, ARCHITECTURE.md, docs/*.md, index.html, wiki/index.html, wiki/i18n-content.js, and server/__tests__/plugins-marketplace.test.js. Grep the old number repo-wide; update every hit.

Workflow B — adding a new language

This is a large, exact, mechanical change. Read references/new-language-checklist.md and work through it top to bottom — it lists every file, in dependency order, with the exact edit for each.

The three things contributors most often ship incomplete, stated up front:

  1. The full-guide mirror must be complete. README-<XX>.md is a full mirror of README-EN.md — every section, every table row, every code block, every mermaid diagram, in the same order. Do not summarize, do not drop "less important" sections, do not stop halfway. Diff the heading list against README-EN.md before you open the PR — the audit script compares heading counts, which catches a truncated mirror but not a reordered or silently condensed one.
  2. Every app key must be translated. All 15 namespaces × every key. The parity test fails on a missing key, but it passes on a key you copied over in English — so read your diff for untranslated leftovers.
  3. The wiki must be translated completely, not just the headings. That means a full <xx> bundle in wiki/i18n-content.js (thousands of body strings), a full <xx> block in T, META, and every entry of ATTRIBUTE_TRANSLATIONS in wiki/script.js. A locale that only fills T renders a page with translated headings over English paragraphs, which is worse than English.
Show full SKILL.md (598 more words)Show less

What stays in English (all surfaces)

Never translate: code inside <code>/backticks, commands, file and directory paths, URLs, env-var names, HTTP methods and status codes, CLI flags, code identifiers, numbers with units, brand and product names (Claude Code, MCP, Codex), Claude Code hook event names (PreToolUse, Stop, …), and Claude Code tool names (Bash, Agent, Read, Edit). Translate only the prose around them. A block that is entirely code or identifiers needs no wiki entry — it correctly falls back to English.

Two different things are spelled Agent. The Claude Code tool named Agent (alongside Bash, Read, Edit) is an identifier and stays literal in every locale, everywhere it appears — hook-event tables, tool lists, event names. The UI noun for an agent (common:agent / common:subagent) is product vocabulary with a per-locale contract, and only that noun has the Spanish exception below. Never carry the exception into the tool name.

The UI noun's contract, asserted by client/src/i18n/__tests__/i18n.test.ts: zh, vi, and ko keep Agent / Subagent literal; es renders them agente / subagente. A new locale must decide this explicitly and add its row to that test.

Terminology, per-locale conventions, and the shared glossary live in references/translation-style.md. Read it before translating; drifting terminology across pages is the most common review comment on localization PRs.

Two traps worth knowing before you edit the wiki

  1. client/tests/wiki-i18n.test.ts parses wiki/script.js by exact source markers. It slices the file between literal strings — " const T = " … "\n\n const PLAIN", " const ATTRIBUTE_TRANSLATIONS = " … "\n const ATTR", " const META = " … "\n const trH" — and evals what it finds. Renaming, reordering, or re-indenting those declarations breaks the test with a confusing error. Add locales inside the existing objects; leave the declaration lines alone.
  2. The wiki's chosen language lives in localStorage["wiki-lang"], not a URL parameter. There is no ?lang= support. First visit falls back to a navigator.language prefix ladder in wiki/script.js. To preview a locale, use the switcher, or run localStorage.setItem("wiki-lang", "<xx>") in the console and reload.

This skill is mirrored for every agent

The canonical copy — and both scripts — live at .claude/skills/i18n-parity/. It is mirrored, with links rewritten to repo-root-relative paths and an agents/openai.yaml interface added, to:

  • .agents/skills/i18n-parity/ (the shared/OpenAI skill tree)
  • .codex/skills/i18n-parity/ (Codex)

Editing this skill means regenerating the mirrors — edit the canonical copy, then run:

bash
bash .claude/skills/i18n-parity/scripts/sync-agent-mirrors.sh

i18n-audit.sh runs that script in --check mode, so a stale mirror is a reported gap rather than silent drift. The mirrors carry no scripts: they point back at the canonical ones by repo-root path.

Verify (do not skip)

bash
# 1. Cross-surface parity: locale sets, namespace files, key parity, switcher
#    entries, wiki bundles, full-guide mirrors and cross-links, agent-skill mirrors.
bash .claude/skills/i18n-parity/scripts/i18n-audit.sh

# 2. UI key/type/interpolation parity + locale formatting
npm run test:client

# 3. Wiki live-DOM coverage, inline tags, metadata, cache versions
cd client && npx vitest run tests/wiki-i18n.test.ts && cd ..

# 4. Documented counts asserted against the source tree
npm run test:server

# 5. The static wiki files and locale JSON are Prettier-managed
npm run format

i18n-audit.sh exits non-zero and names the exact file and locale for every gap. Every check is a structural one — a named thing is present or it is not — with a single exception: the wiki/i18n-content.js bundle-size check is a stub detector (it flags a locale holding under 60% of the largest bundle's entries). Exact per-string wiki coverage is asserted by client/tests/wiki-i18n.test.ts, which walks the live DOM.

State explicitly which surfaces you updated and which you intentionally skipped (with the reason), per the repo's verification policy in CLAUDE.md.

Tips

  • Write the full English guide first and get it right, on all surfaces, before translating anything. Every other locale is derived from it; re-translating because the English moved is the biggest waste in this workflow.
  • To find where a string already lives: grep -rn "<neighbouring English text>" client/src/i18n/locales/en wiki/i18n-content.js wiki/script.js.
  • When adding a language, one locale per subagent is fine for the wiki body bundle (it is large), but keep the full-guide mirror with a single author so the section order and terminology stay coherent.
  • Wiki edits are cache-first: forgetting the CACHE_NAME / ?v= bump means returning visitors never see the translation you just shipped.

© hoangsonww, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in .codex/skills/i18n-parity of hoangsonww/Claude-Code-Agent-Monitor.

  • SKILL.md
  • agents/openai.yaml
  • references/new-language-checklist.md
  • references/translation-style.md

Open the folder on GitHubat commit a06db03

Compare with similar skills

I18n Parity next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

I18n Parity compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
I18n Parity this skillhoangsonww/Claude-Code-Agent-Monitor1.1k—~3.4kAutomated safety check: PassMIT
Impeccablebestofjs/bestofjs3.1k26 repos~2.6kAutomated safety check: PassMIT
Chatbox i18n Translatorchatboxai/chatbox42k—~508Automated safety check: PassGPL-3.0
Internationalization Workflow with i18niOfficeAI/AionUi33k1 repos~1.9kAutomated safety check: PassApache-2.0
Enforce Rules For I18nmoeru-ai/airi50k—~1.5kAutomated safety check: PassMIT
Claude Desktop Chinese Localizationjavaht/claude-desktop-zh-cn7.5k—~1.6kAutomated safety check: PassMIT

Similar skills

  • Impeccable

    bestofjs/bestofjs

    A skill your agent uses when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a…

    3.1k GitHub starsUsed in 26 repos~2.6k tokens
    Frontend & DesignAuto-check passed
  • Chatbox i18n Translator

    chatboxai/chatbox

    Translates new or changed i18n keys from a Chatbox Pro diff, staged changes or a commit range, writing the locale JSON files directly with a built-in glossary.

    42k GitHub stars~508 tokensUpdated 16 days ago
    Frontend & DesignAuto-check passed
  • Standards for keeping all user-facing text translatable: read the i18n config first, use namespaced keys, reuse shared strings and follow the key naming rules.

    33k GitHub starsUsed in 1 repo~1.9k tokens
    Frontend & DesignAuto-check passed
  • Review pending AIRI translations on Crowdin in a batch, then sync them into the repository.

    50k GitHub stars~1.5k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Claude Desktop Chinese Localization

    javaht/claude-desktop-zh-cn

    Adds missing Simplified and Traditional Chinese translations to the Claude Desktop Chinese patch across three layers, then checks how many mappings actually hit.

    7.5k GitHub stars~1.6k tokensUpdated 6 days ago
    Frontend & DesignAuto-check passed
  • Taro UI Guide

    jd-opensource/taro-ui

    Guides installing, configuring, styling and using taro-ui (At* components) in Taro apps for WeChat, Alipay, H5 and React Native.

    4.7k GitHub stars~1.3k tokensUpdated 16 days ago
    Frontend & DesignAuto-check passed

More from hoangsonww/Claude-Code-Agent-Monitor

All 78 skills in this repo
  • Version Release

    hoangsonww/Claude-Code-Agent-Monitor

    Choose and apply the correct semantic version bump for this repository.

    1.1k GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed
  • Budget Set

    hoangsonww/Claude-Code-Agent-Monitor

    Define a spend budget for Claude Code and, optionally, create a cost alert rule that fires when usage crosses the limit, via POST /api/alerts/rules on the Agent Monitor dashboard.

    1.1k GitHub stars~1k tokensUpdated yesterday
    Auto-check passed
  • Cache Efficiency

    hoangsonww/Claude-Code-Agent-Monitor

    Analyze prompt-cache effectiveness for Claude Code usage from the Agent Monitor dashboard — cache hit rate (totalcacheread / (totalcacheread + totalinput)), cachewrite vs cacheread reuse, cache-read…

    1.1k GitHub stars~966 tokensUpdated yesterday
    Auto-check passed
  • Cost Breakdown

    hoangsonww/Claude-Code-Agent-Monitor

    Break down Claude Code costs using the Agent Monitor pricing engine.

    1.1k GitHub stars~845 tokensUpdated yesterday
    Auto-check passed
  • Dag Map

    hoangsonww/Claude-Code-Agent-Monitor

    Render the multi-agent orchestration DAG for a session — parent→child subagent edges, tree depth, and fan-out — from the Agent Monitor workflow intelligence API.

    1.1k GitHub stars~564 tokensUpdated yesterday
    Auto-check passed
  • Dashboard Status

    hoangsonww/Claude-Code-Agent-Monitor

    Quick dashboard health and status overview — checks the Agent Monitor API (port 4820), reports session/agent/event counts from /api/stats, confirms WebSocket connectivity, reads the redacted hook…

    1.1k GitHub stars~600 tokensUpdated yesterday
    Auto-check passed

Questions about I18n Parity

What does I18n Parity do?

MANDATORY for every coding agent and contributor touching localized content — keep all five localization surfaces (dashboard UI keys, wiki page, full mirrored guides, locale-aware formatting…. I18n Parity is an agent skill from hoangsonww/Claude-Code-Agent-Monitor. MANDATORY for every coding agent and contributor touching localized content — keep all five localization surfaces (dashboard UI keys, wiki page, full mirrored guides, locale-aware formatting, language switchers) in parity across every supported language.

When should I use I18n Parity?

I18n Parity fits situations like: tasks that involve Internationalization.

How do I install I18n Parity in Claude Code?

Run `npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill i18n-parity -a claude-code`. Or copy the skill folder (.codex/skills/i18n-parity in hoangsonww/Claude-Code-Agent-Monitor) into .claude/skills/i18n-parity in your project. Claude Code loads it when a task matches its description.

How do I install I18n Parity in Codex?

Run `npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill i18n-parity -a codex`. Or copy the skill folder (.codex/skills/i18n-parity in hoangsonww/Claude-Code-Agent-Monitor) into .agents/skills/i18n-parity in your project. Codex loads it when a task matches its description.

Can I use I18n Parity in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill i18n-parity -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/i18n-parity, .gemini/skills/i18n-parity, .github/skills/i18n-parity and .opencode/skills/i18n-parity in your project.

What does I18n Parity need to run?

Going by SKILL.md and its folder, I18n Parity needs the command-line tools its instructions call (npm, bash, npx and claude).

Does I18n Parity access the network?

SKILL.md contains no URLs. Its commands use npm and npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is I18n Parity safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does I18n Parity use?

I18n Parity is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does I18n Parity use?

About 3.4k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.2k tokens, read only when the agent opens those files.

What are the alternatives to I18n Parity?

Skills that share tags, products or a category with I18n Parity: Impeccable (bestofjs/bestofjs, 3.1k stars), Chatbox i18n Translator (chatboxai/chatbox, 42k stars), Internationalization Workflow with i18n (iOfficeAI/AionUi, 33k stars) and Enforce Rules For I18n (moeru-ai/airi, 50k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains I18n Parity?

hoangsonww (a GitHub user) maintains it in hoangsonww/Claude-Code-Agent-Monitor, which has 1,058 GitHub stars. The repository holds 78 skills in this directory. The repository was last updated on October 10, 2026.

Source: hoangsonww/Claude-Code-Agent-Monitor on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.