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 agentmods add skills/bahayonghang/my-ai-cli-toolkit/windows-dev-process-cleanupnpx skills add bahayonghang/my-ai-cli-toolkit --skill windows-dev-process-cleanupgit clone --depth 1 https://github.com/bahayonghang/my-ai-cli-toolkitWrote 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/bahayonghang/my-ai-cli-toolkit/windows-dev-process-cleanup)<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/windows-dev-process-cleanup"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/windows-dev-process-cleanup.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 | $0.00124 | $0.00785 |
| Opus 5 | $0.00062 | $0.00392 |
| Sonnet 5 | $0.00025 | $0.00157 |
| Haiku 4.5 | $0.00012 | $0.00078 |
Grade A, and why
windows-dev-process-cleanup 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 4d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Windows Dev Process Cleanup
Audit first and use the narrowest profile. Requires Windows and PowerShell 7; replace <skill-dir> with the loaded skill directory.
Workflow
- Audit without side effects:
pwsh -NoLogo -NoProfile -File "<skill-dir>/scripts/audit-dev-processes.ps1" -Mode audit -AsJson
pwsh -NoLogo -NoProfile -File "<skill-dir>/scripts/audit-uwp-backgroundtasks.ps1" -Mode audit -AsJson
-
Treat
blocked,mixed_tree,unknown,identity-missing, protected members, andaudit_status: failedas manual review. -
Select one profile:
- Dev:
safe,playwright-mcp,codex-playwright-safe,safe-plus-codex-playwright, orworkspace-dev-serverwith an existing-WorkspacePath. - UWP:
phone-link-backgroundordolby-backgroundtask. Dolby cleanup terminates only matchingbackgroundTaskHostinstances.
- Preview the exact plan before cleanup:
pwsh -NoLogo -NoProfile -File "<skill-dir>/scripts/audit-dev-processes.ps1" -Mode cleanup -Profile codex-playwright-safe -StaleMinutes 45 -WhatIf -AsJson
pwsh -NoLogo -NoProfile -File "<skill-dir>/scripts/audit-uwp-backgroundtasks.ps1" -Mode cleanup -Profile dolby-backgroundtask -WhatIf -AsJson
Run without -WhatIf only after an explicit cleanup request and an unblocked plan. The scripts recheck identity and affected members; drift fails the precondition.
Phone Link 2.0 Change
-DisablePhoneLinkBackground is deprecated and fails closed. It never writes the registry. Microsoft documents the supported per-app control in Windows Settings under System > Power & battery > Battery usage > Manage background activity. See migration-2.0.md.
Output Contract
Report normalized inputs, affected PIDs/fingerprints, roles/protection, blocked reasons, plan_id, target counts, preconditions, command status, and per-member outcomes. A zero taskkill exit code is not proof of termination.
Process termination is irreversible. Report exports are local files. No registry rollback exists because version 2.0 performs no registry mutation.
What ships with it
27 files 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.
- agents/interface.yaml 1.3 KB
- evals/evals.json 4.7 KB
- evals/output/cases.jsonl 7.3 KB
- evals/output/fixtures/process-safety-scenarios.md 1.2 KB
- manifest.json 1.6 KB
- README.en.md 4.0 KB
- README.md 3.7 KB
- references/migration-2.0.md 1.0 KB
- references/safety-policy.md 3.4 KB
- references/windows-command-contracts.md 2.7 KB
- reports/output_blind_answer_key.json 1.8 KB
- reports/output_blind_pack.json 7.8 KB
- reports/output_blind_pack.md 4.0 KB
- reports/output_execution_runs.json 8.8 KB
- reports/output_execution_runs.md 2.4 KB
- reports/output_quality_scorecard.json 21 KB
- reports/output_quality_scorecard.md 1.8 KB
- reports/output-risk-profile.md 2.9 KB
- reports/security_trust_report.json 2.2 KB
- reports/security_trust_report.md 2.0 KB
- scripts/audit-dev-processes.ps1 28 KB runs code
- scripts/audit-uwp-backgroundtasks.ps1 14 KB runs code
- security/permission_policy.json 5.2 KB
- tests/audit-scripts.test.mjs 26 KB runs code
- tests/fixtures/process-graphs.json 4.0 KB
- tests/fixtures/tasklist-apps-malformed.csv 163 B
- tests/fixtures/tasklist-apps.csv 415 B
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.
- 4d ago First seen · 58 lines · 124 tokens per session scan A 8604beac522e
windows-dev-process-cleanup is a skill published in the GitHub repository bahayonghang/my-ai-cli-toolkit (16 stars, last pushed 2d ago), licensed MIT. It adds 124 tokens to every session and 785 once invoked, about $0.0006 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
docs-build
Build, preview, and validate the Uno documentation website (DocFX) locally — surface real content errors vs expected noise, drive rendered pages with Playwright, and validate external-doc commit bumps in importexternaldocs.ps1 before a PR. Use when working under doc/, editing articles/ markdown, bumping an external…
web
Browse or inspect live web pages.
bilibili-page-reader
Get content from Bilibili videos: official subtitles, danmaku (density/peaks/sample), comments. When no subtitles exist (no 投稿字幕), fall back to downloading audio + ASR transcription via FunASR.
powershell-safe-invocation
Use when writing or running PowerShell on Windows, especially native programs, quoted paths, escaping, pwsh, Start-Process, file operations, or shell troubleshooting.
locus-unity-bridge
Use when an agent needs to inspect or control a real Unity Editor through Locus, especially when Unity MCP is unavailable, a project may lack the Locus package, named-pipe discovery is needed, C# must be executed, or Unity scripts must be recompiled.
host-computer-use
Beta desktop control through the connected A0 CLI host. Use for the user's host/local computer screenshots, screen inspection, menus, native app UI, OS-level clicking, scrolling, typing, or checking computeruseremote status. Use instead of linux-desktop for host/local machine control. Do not use for ordinary browser…