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-websocket-stabilitygit 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-websocket-stability)<a href="https://agentmods.dev/skills/davidtoby/agent-skills/feishu-websocket-stability"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/feishu-websocket-stability/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-websocket-stability"><img src="https://agentmods.dev/badge/skills/davidtoby/agent-skills/feishu-websocket-stability.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 | $0.00085 | $0.01020 |
| Opus 5.5 | $0.00034 | $0.00408 |
| Sonnet 5.5 | $0.00017 | $0.00204 |
| Haiku 4.5 | $0.00009 | $0.00102 |
Grade A, and why
feishu-websocket-stability 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 1mo 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feishu Websocket Stability
Use this skill when Hermes runs in Feishu websocket mode and you need predictable startup and reconnect behavior.
Quick start
- Confirm the adapter is running in
connection_mode=websocket. - Ensure only one local Hermes gateway instance uses a given Feishu
app_id. - Tune reconnect jitter/interval via Feishu platform
extraconfig. - If the SDK resets its own websocket settings during startup, reapply runtime overrides after
_configure(...). - Add ping tuning only when you have an actual idle-connection problem.
- Back all changes with focused gateway tests.
Core lessons from real usage
1. Guard against duplicate local websocket clients
Feishu websocket mode should behave like a single-owner resource per app.
Problem pattern:
- two local Hermes gateway processes start with the same Feishu
app_id - both try to consume the same websocket stream
- behavior becomes ambiguous or unstable
Fix pattern:
- acquire a scoped local lock keyed by the Feishu
app_id - if acquisition fails, stop startup immediately
- surface a clear fatal error that includes the owning PID when available
Recommended behavior:
- fail fast
- mark the error as non-retryable until the competing process is stopped
2. Make reconnect timing configurable
The official Feishu SDK defaults are conservative.
Real effect:
- first reconnect may wait with large jitter
- later reconnects can be spaced far apart
- production recovery after a transient network flap can feel unnecessarily slow
Expose config values under platforms.feishu.extra:
platforms:
feishu:
extra:
ws_reconnect_nonce: 0
ws_reconnect_interval: 3
Guideline:
ws_reconnect_nonce: non-negative integerws_reconnect_interval: positive integer- invalid values should fall back to SDK defaults instead of crashing startup
3. Runtime websocket overrides must survive SDK reconfiguration
A subtle failure mode:
- you set local reconnect or ping values
- the Feishu SDK later calls its own
_configure(...) - your custom values get overwritten
- reconnect tuning appears ignored even though config parsing worked
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.
- 1mo ago First seen · 148 lines · 85 tokens per session scan A 26d89a091207
feishu-websocket-stability is a skill published in the GitHub repository davidtoby/agent-skills (11 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 1,020 once invoked, about $0.0003 per session on Opus 5.5. 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
doris-debug-deployment
Use for Doris FE/BE startup failures, port conflicts, prioritynetworks misrouting, metadir corruption, and ADD/DROP BACKEND issues.
pipehero
Tunnel localhost to a public URL — debug webhooks (inspect and replay captured requests, and via the Pipehero MCP server let the agent read captured webhooks and diagnose failing handlers against the code), expose your own MCP server (Streamable HTTP) so a cloud-only client like Claude.ai or ChatGPT can reach it, or…
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.
new
Create a new project to start development quickly.
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…