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 Wals-pro/claude-power-automate --skill power-automate-run-forensicsgit clone --depth 1 https://github.com/Wals-pro/claude-power-automateWrote 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/wals-pro/claude-power-automate/power-automate-run-forensics)<a href="https://agentmods.dev/skills/wals-pro/claude-power-automate/power-automate-run-forensics"><img src="https://agentmods.dev/badge/skills/wals-pro/claude-power-automate/power-automate-run-forensics/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/wals-pro/claude-power-automate/power-automate-run-forensics"><img src="https://agentmods.dev/badge/skills/wals-pro/claude-power-automate/power-automate-run-forensics.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 | $0.00071 | $0.00351 |
| Opus 5 | $0.00036 | $0.00176 |
| Sonnet 5 | $0.00014 | $0.00070 |
| Haiku 4.5 | $0.00007 | $0.00035 |
Grade A, and why
power-automate-run-forensics 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.
What it actually says
Power Automate Run Forensics
Start read-only. Confirm what the flow actually did before changing JSON, connections, or production records.
Procedure
- Define boundary: profile, environment ID, flow ID/name, run ID(s), object IDs, and absolute time window.
- Run
power-automate status --profile <profile>andpower-automate runs --profile <profile>when API access is available. - If the flow or environment is unknown, run
power-automate environments,power-automate flows, orpower-automate runs --all-environments --top <n>to discover what the signed-in Azure user can see. - For a failed or suspicious run, inspect
power-automate run-detail. - Compare trigger data, action inputs, action outputs, branch status, skipped actions, and connector error codes.
- Read
references/errors-limits.mdfor Microsoft error/limit guidance. - Produce findings before proposing edits.
Output
Report:
- Boundary checked.
- Evidence reviewed.
- Findings with run IDs and timestamps.
- Impact.
- Root cause or strongest hypothesis.
- Fix target and validation plan.
If evidence is missing, name the missing source and why it matters.
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.
- 12d ago First seen · 43 lines · 71 tokens per session scan A 6e38698b9ee9
power-automate-run-forensics is a skill published in the GitHub repository Wals-pro/claude-power-automate (11 stars, last pushed 2d ago), licensed MIT. It adds 71 tokens to every session and 351 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 2026-08-31.
Other skills, from other repositories
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
doris-debug-deployment
Use for Doris FE/BE startup failures, port conflicts, prioritynetworks misrouting, metadir corruption, and ADD/DROP BACKEND issues.
kirby-debugging-and-tracing
Diagnoses Kirby rendering/runtime issues using MCP runtime rendering, dump traces, and template/snippet/controller indexes. Use when outputs are wrong, errors occur, or tracing execution paths is required.
performance-optimizer
Systematic performance profiling and optimization for Python and web backends — measure first, fix second, verify the fix.
error-handling
Implement robust error handling with custom error types, proper propagation, user-friendly messages, and logging. Use when adding error handling to APIs, libraries, or applications.
backend-performance
Diagnóstico y optimización de performance backend: medir antes de optimizar, cachés correctas, batching, índices, conexiones, async, perfiles de CPU/IO. Cargá cuando hay un cuello reportado o un endpoint crítico.