Borrowing it
Nothing to install: this file belongs to OwnOptic/power-automate-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/OwnOptic/power-automate-mcp/main/.claude/skills/debug-flow/SKILL.mdgit clone --depth 1 https://github.com/OwnOptic/power-automate-mcpWrote 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/ownoptic/power-automate-mcp/debug-flow)<a href="https://agentmods.dev/skills/ownoptic/power-automate-mcp/debug-flow"><img src="https://agentmods.dev/badge/skills/ownoptic/power-automate-mcp/debug-flow.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.00624 |
| Opus 5 | $0.00034 | $0.00312 |
| Sonnet 5 | $0.00014 | $0.00125 |
| Haiku 4.5 | $0.00007 | $0.00062 |
Grade A, and why
debug-flow 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 6d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug a Power Automate flow
Work the loop in order. Skip a step only when you already hold its output.
- Resolve the flow.
list_flows, match ondisplay_name, keep theflow_id. - Find the failure.
list_runs(flow_id, status="Failed"). Newest first. - Diagnose one run.
explain_run(flow_id, run_id)on the newest failed run.failed_actions[].erroris the real error text, already resolved from the SAS-signed blob. Do not go fetch it yourself.failed_actionsempty while status is Failed means the TRIGGER failed.get_flowand inspect the trigger's condition and inputs.- The cause is usually upstream: read the
succeededoutputs for the value that fed the failing action.
- Error clear but cause not ("it worked yesterday", intermittent,
data-dependent):
compare_runs(flow_id, failed_run_id). It auto-picks the most recent Succeeded run as baseline. Readdiverged_atfirst, thenoutput_changes- an action that succeeded in both runs with different output is usually the real cause.only_in_failed/only_in_baselinemeans a condition or branch evaluated differently. - Recurring or flaky:
analyze_flow_health(flow_id). Trust theverdict:- broken (near-100% failure) - fix the definition, stop rerunning it
- flaky, concentrated in one action - targeted fix on that action
- flaky, spread across actions - suspect trigger data or a connection, not logic
- Fix and verify.
get_flow-> edit the returneddefinition->update_flow_definitionwith the COMPLETE definition (there is no partial update). Re-run withrun_flow, thenexplain_runagain to confirm.
Rules learned the hard way
- SAS URLs on old runs expire. If
explain_runreports the error blob unavailable, re-run the flow and diagnose the fresh run instead of digging. run_flowdoes not forward a body:@triggerBody()is null when triggered through the management API. If the failure only reproduces with a real payload, call the flow's actual HTTP trigger URL.- Deterministic vs data-dependent: the same action failing in both compared runs
with empty
output_changesmeans the definition is wrong. Different upstream outputs mean the data is.
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.
- 6d ago First seen · 43 lines · 68 tokens per session scan A 34558b8308b4
debug-flow is a skill published in the GitHub repository OwnOptic/power-automate-mcp (0 stars, last pushed 21d ago), licensed MIT. It adds 68 tokens to every session and 624 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
broken-link-auditor
Audits SharePoint pages, news posts, and hyperlink fields for broken or risky links and saves a self-contained HTML link-health report to the site. It is strictly read-only for content and only writes the final report file. Use when the user says: "broken link audit" "find broken links" "check dead links on this site"…
ralphctl-debugging-and-error-recovery
Systematic root-cause debugging. Use when tests fail, builds break, or behaviour does not match expectations. Follow stop-the-line → reproduce → localize → reduce → root-cause → guard-with-regression-test → verify, not guessing; the reproduction and regression steps follow the same red-green discipline as…
code
Use BEFORE generating, refactoring, reviewing, or debugging code. Trigger phrases include "write a function/script/class for X", "review this code/diff/PR", "refactor this", "debug this error", "is this implementation correct", "what's wrong with this code", "improve this code", "translate from X to Y", or any prompt…
sentry
Query Sentry issues, events, releases, replays, and org/project metadata via REST API. Use when the user wants to diagnose a production error, pull stack traces, list recent issues, inspect a release, or fetch event data programmatically — prefer this over asking for UI screenshots or guessing from memory.
opengrok
Use this skill whenever the user wants to search, navigate, or understand source code in a large codebase — even when they don't say "OpenGrok". Trigger for: finding where a function or class is defined, tracking where something is called or referenced, reading a remote source file, checking who last changed a line…
opengrok-investigation
Use this skill when conducting a structured investigation into a bug, unknown module, or impact analysis using OpenGrok. Provides step-by-step methodology for systematic codebase investigation with memory-backed state management. Trigger when: diagnosing a bug with unknown root cause, exploring an unfamiliar module…