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 Sunne927/Codex-CLI-Bridge-for-Lark-Feishu --skill feishu-codex-linkergit clone --depth 1 https://github.com/Sunne927/Codex-CLI-Bridge-for-Lark-FeishuWrote 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/sunne927/codex-cli-bridge-for-lark-feishu/feishu-codex-linker)<a href="https://agentmods.dev/skills/sunne927/codex-cli-bridge-for-lark-feishu/feishu-codex-linker"><img src="https://agentmods.dev/badge/skills/sunne927/codex-cli-bridge-for-lark-feishu/feishu-codex-linker/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/sunne927/codex-cli-bridge-for-lark-feishu/feishu-codex-linker"><img src="https://agentmods.dev/badge/skills/sunne927/codex-cli-bridge-for-lark-feishu/feishu-codex-linker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 62 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00077 | $0.01320 |
| Opus 5 | $0.00039 | $0.00660 |
| Sonnet 5 | $0.00015 | $0.00264 |
| Haiku 4.5 | $0.00008 | $0.00132 |
Grade A, and why
feishu-codex-linker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- feishu-codex-linker — 91% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feishu Codex Linker
Use this skill when the user wants the bridge installed or repaired with the feishu pack.
Default language follows the user's recent messages. Keep the interaction short and action-oriented.
Before acting, read references/install-strategy.md.
The goal is not just "service up". The goal is "Feishu text ingress works, authorization binds, and interactive card callbacks work".
Do not stop after ctb doctor is green or /status replies once. For the current implementation, Feishu setup is only complete after both of these paths are proven:
- text ingress path:
im.message.receive_v1 - card callback path:
card.action.trigger
Resolve these first:
SKILL_ROOT="${CODEX_HOME:-$HOME/.codex}/skills/feishu-codex-linker"
INSTALL_SCRIPT="$SKILL_ROOT/scripts/install-bridge-from-github.sh"
CTB_BIN="${HOME}/.local/share/codex-telegram-bridge/bin/ctb"
Windows PowerShell equivalents:
$codexHome = if ($env:CODEX_HOME) { $env:CODEX_HOME } else { Join-Path $HOME ".codex" }
$localAppData = if ($env:LOCALAPPDATA) { $env:LOCALAPPDATA } else { Join-Path $HOME "AppData\\Local" }
$skillRoot = Join-Path $codexHome "skills\\feishu-codex-linker"
$installScript = Join-Path $skillRoot "scripts\\install-bridge-from-github.ps1"
$ctbBin = Join-Path $localAppData "codex-telegram-bridge\\bin\\ctb.cmd"
For first install, use the bundled script:
bash "$INSTALL_SCRIPT" --pack feishu --feishu-app-id '<app_id>' --feishu-app-secret '<app_secret>' --project-scan-roots '<path1:path2:path3>'
The bundled script requires an authenticated GitHub CLI, clones Sunne927/Codex-CLI-Bridge-for-Lark-Feishu, and builds locally. Do not use public archive installers or expose GitHub credentials in shell commands.
On Windows:
powershell -ExecutionPolicy Bypass -File $installScript -Pack feishu -FeishuAppId '<app_id>' -FeishuAppSecret '<app_secret>' -ProjectScanRoots '<path1;path2;path3>'
Rules:
- do as much as possible automatically
- detect before asking
- ask for one thing at a time
- use the bundled install script for first install
- use
ctbfor status, doctor, restart, update, authorize, and repair flows - ask only for Feishu app credentials, Codex login, one project-root decision if needed, or one Feishu P2P message to the bot
- prefer
ctb status,ctb doctor,ctb restart, andctb authorize ...over reinstalling - do not ask the user to run local shell commands you can run yourself
- do not declare success until readiness is healthy, authorization is bound,
/statussucceeds,/newrenders, and one project-card button click succeeds
Required Feishu-side config for the current pack:
- enterprise self-built app
- bot ability enabled
- permission
im:message.p2p_msg:readonly - long connection enabled
- event subscription
im.message.receive_v1 - card callback
card.action.trigger - publish the latest app version after changing permissions or events
Known operator traps:
- text reply working once does not prove card callbacks are configured
/newrendering does not prove button callbacks are configured- if text messages never reach the bridge, another consumer on the same Feishu app may be taking the events; OpenClaw is one known example
- if button clicks fail with
200340, treat that as Feishu card callback access/config not effective, not as a project-picker bug - if install came from an older public GitHub archive, reinstall from the authorized target repository before deep debugging
Minimal finish flow:
- Confirm install or repair state with
ctb statusandctb doctor. - Confirm the Feishu app has the required config as one checklist, not one-by-one guesswork.
- Ask the user to send one private message to the bot if authorization is pending.
- Bind with
ctb authorize .... - Verify
/status. - Verify
/new. - Verify one project-card button click.
Failure interpretation:
- no response to private message:
check bot ability,
im:message.p2p_msg:readonly, long connection,im.message.receive_v1, published version, and shared-app contention - private message works but button click fails:
check
card.action.triggerand publish the latest app version again - reply says account is not bound:
continue with
ctb authorize pendinginstead of reinstalling ctb authorize ...hits a state-store lock: treat that as a local service/admin coordination problem, not a Feishu permission problem
What ships with it
4 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.
- 10d ago First seen · 132 lines · 77 tokens per session scan A c438c41b1a3b
feishu-codex-linker is a skill published in the GitHub repository Sunne927/Codex-CLI-Bridge-for-Lark-Feishu (31 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 1,320 once invoked, about $0.0004 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
article-writer
Multi-style article creation skill. Supports 5 writing styles (deep analysis, practical guide, story-driven, opinion, news brief), including complete workflow: material collection → outline → content → formatting. Activated when users mention "write article", "write post", "create", or "draft".
skin-creator
Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.
content-planner
WeChat Official Account topic planning and content calendar management. Based on WeChat article search and trending analysis, generates differentiated topic recommendations and outputs structured content calendars. Activated when users mention "topic", "planning", "content calendar", "trending", or "what to write next…
music-search
Search cloud drives for downloadable music resources (songs, albums, lossless audio). Use this skill when the user wants to download a specific song or album. Do NOT use for general music information, lyrics, or recommendations.
stock-analyzer
A comprehensive stock deep analysis tool that combines real-time quotes, fundamental metrics, technical indicators, and growth analysis into a single professional report. Supports A-share, US stocks, HK stocks. Generates detailed investment recommendations with risk assessment and actionable trading strategies.
weather
Get current weather and forecasts (no API key required).