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 davidtoby/agent-skills --skill feishu-approval-fallbackgit clone --depth 1 https://github.com/davidtoby/agent-skillsWrote 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/davidtoby/agent-skills/feishu-approval-fallback)<a href="https://agentmods.dev/skills/davidtoby/agent-skills/feishu-approval-fallback"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/feishu-approval-fallback/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/davidtoby/agent-skills/feishu-approval-fallback"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/feishu-approval-fallback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00082 | $0.01118 |
| Opus 5 | $0.00041 | $0.00559 |
| Sonnet 5 | $0.00016 | $0.00224 |
| Haiku 4.5 | $0.00008 | $0.00112 |
Grade A, and why
feishu-approval-fallback 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 5d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feishu Approval Fallback
Use this skill when Hermes command approvals on Feishu become unreliable.
Quick start
- Confirm whether the symptom is Feishu-side button failure (
200340) or Hermes-side callback/state mismatch. - Check whether the current adapter supports text fallback mode and inline callback-card resolution.
- Normalize
approval_idhandling to strings end-to-end. - Keep approval resolution in the synchronous callback response path when Feishu clients need immediate button feedback.
- Always provide text fallback instructions when button clicks may fail.
- Back the fix with focused gateway tests.
Core lessons from real usage
1. Treat Feishu 200340 as an expected integration failure mode
Feishu interactive approval cards can send successfully while button clicks still fail if app-console configuration is incomplete.
Practical consequence:
- the user sees the card
- clicking the button fails
- the approval flow must still remain usable
Therefore:
- do not rely exclusively on interactive buttons
- provide a text fallback path
2. Keep approval_id as a string everywhere
Feishu callback payloads may coerce button values to strings depending on SDK and transport details.
Guideline:
- generate
approval_idasstr(next(...)) - store
_approval_statekeyed bystr - convert callback
approval_idtostr(...)before lookup/pop
Do not mix int keys on send with string values on callback.
3. Return the resolved card from the synchronous callback path
For approval button clicks, Feishu clients expect the callback response itself to carry the final resolved card state.
Do this:
- parse the card action synchronously in
_on_card_action_trigger - build the resolved approval card immediately
- return it in
P2CardActionTriggerResponse - schedule the agent-unblocking work on the loop separately
Do not depend on a later async message update to make the button state look resolved.
4. Separate UI acknowledgement from agent unblocking
What ships with it
1 file 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.
- 5d ago First seen · 150 lines · 82 tokens per session scan A 130c85010666
feishu-approval-fallback is a skill published in the GitHub repository davidtoby/agent-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 1,118 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 2026-09-03.
Other skills, from other repositories
clawdbot-logs
Analyze Clawdbot logs and diagnostics. Use when the user asks about bot performance, response times, errors, session stats, token usage, API costs, or wants to debug slow responses.
ai-code-review
AI-powered code review for staged git changes. Catches bugs, security issues, and code smells before you push.
officecli-academic-paper
Use this skill to build academic-style .docx output: journal / conference / thesis chapters carrying formal citation style (APA, Chicago, IEEE, MLA), numbered equations, figure & table cross-references, footnotes/endnotes, bibliography, or multi-column journal layout. Trigger on: 'research paper', 'journal paper'…
officecli
Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.
triage-issue
Analyze a GitHub issue, verify claims against the codebase, and close invalid issues with a technical response.
webflow-code-component:troubleshoot-deploy
Debug deployment failures for Webflow Code Components. Analyzes error messages, identifies root causes, and provides specific fixes for common issues.