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 tpierrain/kenjaku --skill mcp-token-expiredgit clone --depth 1 https://github.com/tpierrain/kenjakuWrote 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/tpierrain/kenjaku/mcp-token-expired)<a href="https://agentmods.dev/skills/tpierrain/kenjaku/mcp-token-expired"><img src="https://agentmods.dev/badge/skills/tpierrain/kenjaku/mcp-token-expired/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/tpierrain/kenjaku/mcp-token-expired"><img src="https://agentmods.dev/badge/skills/tpierrain/kenjaku/mcp-token-expired.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00769 |
| Opus 5 | $0.00043 | $0.00385 |
| Sonnet 5 | $0.00017 | $0.00154 |
| Haiku 4.5 | $0.00009 | $0.00077 |
Grade A, and why
mcp-token-expired 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 12d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expired MCP token — visual alert + reconnection
As soon as a tool of a native claude.ai connector (Slack, Gmail, Calendar, Notion, Google Drive)
returns an authentication error (invalid_auth_token, not_authed, token_expired,
auth_failed…), run the procedure below.
⚠️ Exception: a connector that is unavailable by design
Some connectors may be unavailable by design — not because of an expired token, but because an org policy or a provider restriction blocks them for this account. This is not a token to refresh: do NOT show the alert below and do NOT run the reconnection. Treat the connector as an unavailable source by default: use the fallback, briefly note " unavailable (org/provider restriction)", and continue without blocking.
Procedure (real authentication error)
-
Immediately show this alert block (as-is, emojis included):
🚨🚨🚨 MCP TOKEN EXPIRED 🚨🚨🚨 ⚠️ Connector: <name> (mcp__claude_ai_<...>) ⚠️ Error: <error code> 🔌 Impact: <what becomes unavailable> → fallback used. 👉 TO RECONNECT: type /mcp → select <connector> → Re-authenticate (browser OAuth flow, ~20 s, and everything works again) 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 -
Push
/mcpin the terminal as the first attempt. If the token is simply expired and/mcpoffers a re-authentication, this is the fastest path. -
If
/mcpshowsconnectedbut the call still fails withinvalid_auth_token→ the downstream token is stale despite the "connected" status; a/mcpwill not regenerate it (it believes it is already connected). Real fix:DisconnectthenReconnectthe connector on claude.ai (open "https://claude.ai/settings/connectors"). On reconnect, explicitly authorize the right account / workspace (the SSO or identity this connector expects) — otherwise the connector stays "connected" but on an invalid token. -
Continue with the fallback without blocking (e.g. an alternative MCP connector, or a channel/timestamp search for Slack — see the Sourcing rule in CLAUDE.md). Do not stop and wait for the reconnection.
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.
- 12d ago First seen · 59 lines · 85 tokens per session scan A becf4badc1bf
mcp-token-expired is a skill published in the GitHub repository tpierrain/kenjaku (82 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 769 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
lint
A health check for the LLM Wiki, a knowledge base about large language models. It looks for missing pages, broken links, conflicting or outdated content, missing fields, incomplete topic maps, weak bias checks, and an old core-context snapshot.
refresh-context
A context snapshot updater for Core Context.md, a summary file built from nine main system files and selected essays. It refreshes that summary when the underlying material changes or the snapshot is more than 30 days old.
status
A status report for the LLM Wiki, a knowledge base about large language models. It summarizes counts, recent activity, unfinished Inbox items, index differences, required field coverage, and the age of the core-context snapshot.
capture-tabs
A capture skill that saves groups of Chrome tabs, browser research, or AI chat sessions as Markdown files in an LLM Wiki inbox.
reindex
A search-index rebuild command for the LLM Wiki, its original-source files, and saved queries. An index is a lookup structure that helps search find relevant content.
ingest
A tool for adding a URL, file, text, or Inbox item to the LLM Wiki. It checks the material's purpose, preserves the original source, compiles a wiki page, updates indexes and logs, and reviews the result.