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/list-appsnpx skills add microsoft/managed-apps --skill list-appsgit 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 | $0.00036 | $0.00704 |
| Opus 5 | $0.00018 | $0.00352 |
| Sonnet 5 | $0.00007 | $0.00141 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
list-apps 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 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.
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 — 73 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.
List Apps
Lists apps the active CLI account can see in the active environment, or shows full metadata for a single app.
Workflow
- Memory Bank → 2. Verify Env → 3. Mode (list / show) → 4. Output
Step 1: Check Memory Bank
If a project memory bank exists, read it for the app's environment, if recorded, to know which environment the app was created in. Otherwise prompt the user for the environment they want to query (or accept "current default"). Note: ms app list reports apps for the signed-in account's resolved environment and has no environment-targeting flag, so the memory bank here is for context/verification — it does not scope the listing.
Step 2: Verify Env
BIN=ms
$BIN auth status # confirm the right account
The listing scopes to the active environment (the auto-routed Developer environment unless a specific one was targeted at create time).
Step 3: Mode
Ask (or infer from the user's prompt):
- list — enumerate all apps the account can see.
- show — full metadata for one app (display name, GUID, environment, version, build info, share count, creation/modification dates).
Step 4: Output
List:
$BIN app list --json
Pretty-print the JSON. Default columns when summarizing for the user: displayName | appId | environmentId | version | lastModified.
If the list is long (>20 entries), ask the user whether they want to filter (by display-name substring) before printing. The CLI itself returns everything; the filtering happens in this skill.
Show:
$BIN app show --app "$APP_ID" --json
Pretty-print the full envelope. Highlight: appId, displayName, environmentId, version, lastDeployedCommit, shareCount, and any status fields surfaced by the service.
Useful as a Subroutine
Other skills (/delete-app, /share, /deploy) can invoke this skill to resolve an app GUID from a display-name substring. When invoked as a subroutine, take the search term as $ARG1 and return only the matching appId / displayName pairs — skip the interactive prompts.
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 · 73 lines · 36 tokens per session scan A 0a9852eb9e5b
list-apps is a skill published in the GitHub repository microsoft/managed-apps (5 stars, last pushed 5d ago), licensed MIT. It adds 36 tokens to every session and 704 once invoked, about $0.0002 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
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…