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.
git clone --depth 1 https://github.com/celigo/aiWrote 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/commands/celigo/ai/celigo-troubleshoot)<a href="https://agentmods.dev/commands/celigo/ai/celigo-troubleshoot"><img src="https://agentmods.dev/badge/commands/celigo/ai/celigo-troubleshoot/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/commands/celigo/ai/celigo-troubleshoot"><img src="https://agentmods.dev/badge/commands/celigo/ai/celigo-troubleshoot.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 | $0.00045 | $0.00622 |
| Opus 5.5 | $0.00018 | $0.00249 |
| Sonnet 5.5 | $0.00009 | $0.00124 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade A, and why
celigo-troubleshoot 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.
What it actually says
Help me find out why a Celigo flow isn't doing what it should. Follow the troubleshooting-flows skill -- its Read Before You Answer order, Problem Categories, Error Diagnosis Framework, and Diagnostic Workflow -- and run its steps with the tools you have: the Celigo MCP server's tools (that skill's references/mcp.md) or the celigo CLI (references/cli.md). With neither, work from what I paste: error messages, a job summary, or the flow, export, or import JSON.
Start from what I've given you and what the account shows. Ask me only for what you can't find there:
- Which flow, in which account and environment (with an id or a name, look it up rather than asking)
- The symptom -- a failed run, some records erroring, a run that brought nothing, a stuck or slow run, a schedule that didn't fire, or wrong data with no errors
- When it started, and what changed around then (the audit log usually answers this)
Then:
- Read the flow's latest runs and their per-step jobs (Diagnostic Workflow step 1), and name the problem category.
- For errors, start with the step I mean -- for "the most recent error", the latest by time; otherwise the step with the most. Group its errors by message, read a few records' retry data and request/response, and read the configuration those errors point at: the mapping row, lookup, request body, filter, hook or connection (steps 2-4). Classify each error by its
classification, not its HTTP status. - For an empty run, a stuck run, a missed schedule, or wrong output with no errors, use the skill's matching section (Empty Run, Stuck-Flow Triangulation, Missed Scheduled Runs, step 5's stage checks) and the execution logs of a run that captured them (step 6).
- Report the root cause with the evidence for it, keeping what the reads prove apart from what you infer, and give the fix: the configuration change, or the record data to correct before a retry. Before suggesting a retry or a re-run, say what it will do: a retry fails again until the cause is fixed, and a re-run after a canceled or failed run can write again what an import already wrote.
Diagnosis is read-only. A test run (step 5) writes nothing to the destination, but it reads the source and runs the flow's hooks for real -- say so before starting one. Wait for my yes before anything that writes: arming execution logging, running the flow, retrying or resolving errors, or changing configuration. Then follow steps 8 and 9: prove the fix on one record before retrying the rest.
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 Changed c2bc51bd2ce3
- 6d ago First seen · 21 lines · 45 tokens per session scan A c779478377bc
celigo-troubleshoot is a command published in the GitHub repository celigo/ai (4 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 622 once invoked, about $0.0002 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 2026-10-22.
Other commands, from other repositories
doctor
Diagnose the PyWry install (Python interpreter, pywry[mcp] extra, native binary, MCP server reachability).
fire-resurrect
Autonomous Resurrection Mode — reverse-engineer intent from messy code, then rebuild clean from scratch.
fire-reflect
After any failure (debug resolution, test failure, approach rotation, stalled loop), capture what was tried, why it failed, and what actually worked as a persistent reflection. Future sessions search these before investigating.
fire-verify-uat
Conversational User Acceptance Testing with automatic parallel diagnosis on failures.
http-service
Build, review or debug a Bun HTTP service. Loads the http-service skill, then works the task through its workflow.
pn-audit-api
Surgical API design review — REST conventions, status codes, response shapes, validation, and schema leaks. Use standalone or as part of pn-backend-audit. Outputs a scored fix roadmap.