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/microsoft/managed-apps/delete-appnpx skills add microsoft/managed-apps --skill delete-appgit clone --depth 1 https://github.com/microsoft/managed-appsWhat 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 | $0.00028 | $0.00941 |
| Opus 5 | $0.00014 | $0.00470 |
| Sonnet 5 | $0.00006 | $0.00188 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade C, and why
delete-app scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf <project-dir> How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
📋 Shared Instructions: shared-instructions.md — Cross-cutting concerns. Two confirmations required; never auto---force.
Delete App
Removes the app from the service. The local workspace is NOT deleted by this skill — the user can clean it up afterward (this skill suggests the command but doesn't run it).
Workflow
- Memory Bank → 2. Resolve App ID → 3. Verify with Show → 4. First Confirmation → 5. Try Non-Force Delete → 6. If Service Says Force Required: Second Confirmation → 7. Suggest Local Cleanup → 8. Update Memory Bank
Step 1: Check Memory Bank
Read memory-bank.md for app slug + GUID + environment.
Step 2: Resolve App ID
test -f ms.config.json && APP_ID=$(node -p "require('./ms.config.json').appId" 2>/dev/null) || true
If no ms.config.json, ask the user for the app slug or GUID. Optionally invoke /list-apps to discover.
Step 3: Verify with Show
Before the destructive call, fetch the app metadata so the user sees what they're about to delete:
BIN=ms
$BIN app show --app "$APP_ID" --json
Display: display name, slug, app GUID, environment, version, creation date, last modified, share count if available.
Step 4: First Confirmation
"About to delete the app
<display-name>(slug<slug>, GUID<guid>) from environment<env-name>. This removes the app from the service for all users — playing the app stops working immediately. Continue?"
Wait for explicit yes. If no, STOP — do not delete.
Step 5: Try Non-Force Delete
$BIN app delete --app "$APP_ID" --non-interactive
ms app delete is idempotent: if the app is already gone (HTTP 204) it emits a warning rather than erroring. Treat both existed: true and existed: false outcomes as success.
Step 6: If Service Says Force Required
If the service returns a non-2xx with a message like "delete requires --force" (the app has active shares, child resources, etc.), DO NOT auto-add --force. Instead, ask a second confirmation:
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.
- yesterday First seen · 99 lines · 28 tokens per session scan C 3089d16b6ede
delete-app is a skill published in the GitHub repository microsoft/managed-apps (5 stars, last pushed 5d ago), licensed MIT. It adds 28 tokens to every session and 941 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…