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 obto-inc/platform --skill obto-troubleshootinggit clone --depth 1 https://github.com/obto-inc/platformWrote 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/obto-inc/platform/obto-troubleshooting)<a href="https://agentmods.dev/skills/obto-inc/platform/obto-troubleshooting"><img src="https://agentmods.dev/badge/skills/obto-inc/platform/obto-troubleshooting/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/obto-inc/platform/obto-troubleshooting"><img src="https://agentmods.dev/badge/skills/obto-inc/platform/obto-troubleshooting.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 | $0.00096 | $0.03872 |
| Opus 5.5 | $0.00038 | $0.01549 |
| Sonnet 5.5 | $0.00019 | $0.00774 |
| Haiku 4.5 | $0.00010 | $0.00387 |
Grade A, and why
obto-troubleshooting 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OBTO Troubleshooting
Read the envelope first
OBTO tools return structured errors: {ok:false, error:<code>, hint:<what to do>}. The hint is authoritative — follow it before improvising. An "error" string inside an ok:true payload is NOT a failure.
After an OBTO update
When OBTO announces a release, a tool is missing or behaves the old way, or the server seems wrong, call obto_whoami and read sessionVersion, podVersion and sessionStale:
sessionStale: true— this connection was opened before the server was updated. New tools are absent from your tool list, and existing tools may still run their old code while answeringok.sessionStale: false, but a tool named in the release note is missing from your tool list — the client cached the old list.sessionStale: null— the server could not tell; judge by the tool list.
In each case tell the user in one line: reconnect the OBTO connector (Claude app: Settings > Connectors; Claude Code: /mcp > Reconnect; Codex: restart Codex), then start a new chat or thread, because an open chat keeps the tool list it started with. Do not retry the missing tool or imitate it with other tools; after the reconnect, obto_whoami in the new chat should show sessionStale: false and the new tools.
A connector with no tools
When the user names a connector and it has no tools, stop and say exactly: "the connector has no tools: check its URL with codex mcp list / claude mcp list; it must end in /ms/mcp". Never continue on another connector: each may be a different cluster. A hand-added entry with a plugin's name shadows the plugin's own entry; the fix is codex mcp remove <name>, then codex mcp login <name>.
Common errors and what they actually mean
-32602 missing appName/domain — the stateless contract: every call carries both explicitly. Get domain from obto_whoami; ask the user which app.
cross_tenant_not_allowed — the call passed a domain other than the signed-in identity's own, and the identity is not a super-user. Only super-users (dev-domain identity) may address other tenants. Use the identity's own domain, or have an operator run the call.
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 Changed · +2 tokens per session dfd388a5e398
- 16d ago Changed 59808923bee4
- 18d ago Changed · +19 lines · +14 tokens per session 58573f464473
- 2mo ago Changed · +20 lines de37a7b2fbfd
- 2mo ago First seen · 85 lines · 80 tokens per session scan A e50cf3db81dd
obto-troubleshooting is a skill published in the GitHub repository obto-inc/platform (1 stars, last pushed 12d ago), licensed Apache-2.0. It adds 96 tokens to every session and 3,872 once invoked, about $0.0004 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 2026-08-31.
obto-troubleshooting compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| obto-troubleshootingobto-inc/platform | Skill | 1 | 12d ago | Apache-2.0 | A | 96 | Claude Code, Codex |
| chrome-devtools-cliChromeDevTools/chrome-devtools-mcp | Skill | 55k | yesterday | Apache-2.0 | A | 31 | Claude Code |
| n8n-error-handlingczlonkowski/n8n-mcp | Skill | 23k | yesterday | MIT | A | 128 | Claude Code, Codex |
| n8n-validation-expertczlonkowski/n8n-mcp | Skill | 23k | yesterday | MIT | A | 91 | Claude Code, Codex |
| agentcore-investigationawslabs/mcp | Skill | 9.9k | yesterday | Apache-2.0 | A | 52 | Claude Code, Codex |
| temps-plugingotempsh/temps | Skill | 903 | yesterday | Apache-2.0 | A | 92 | Claude Code, Codex |
| analyze-dumpsvnscha/mcp-windbg | Skill | 1.7k | 9d ago | MIT | A | 56 | Claude Code |