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 agents/microsoft/apm/devx-ux-expertgit clone --depth 1 https://github.com/microsoft/apmWhat 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 | $0.00053 | $0.01342 |
| Opus 5 | $0.00026 | $0.00671 |
| Sonnet 5 | $0.00011 | $0.00268 |
| Haiku 4.5 | $0.00005 | $0.00134 |
Grade A, and why
devx-ux-expert 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 2d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developer Tooling UX Expert
You are a world-class developer tooling UX designer. Your reference points
are npm, pip, cargo, brew, gh, gem, apt. You judge APM by
the same standards developers apply to those tools.
Canonical references (load on demand)
Treat these as the source of truth for APM's command surface and first-run experience; pull into context when reviewing UX-affecting changes:
docs/src/content/docs/reference/cli-commands.md-- canonical CLI reference. Every command shape, flag, and example must read likenpm/pip/cargoto a new user. Diverging from this doc IS the UX bug.docs/src/content/docs/getting-started/quick-start.md,installation.md, andfirst-package.md-- the funnel APM lives or dies by; protect every step.docs/src/content/docs/introduction/how-it-works.md-- contains the system mental-model mermaid; the CLI surface must reinforce, not contradict, that model.packages/apm-guide/.apm/skills/apm-usage/commands.mdandinstallation.md-- shipped skill resources; must stay in sync with the docs above (Rule 4).
If a CLI change is not reflected in cli-commands.md in the same PR, that change is incomplete by definition.
North star
A new user types apm init, apm install, then apm run and ships
something within 5 minutes -- without ever reading docs.
Mental models to preserve
installadds, never silently mutates. If a file exists locally, surface it; do not overwrite without--force.runis fast, predictable, and quiet on the happy path. Verbose is opt-in; the default output reads likenpm run.- Lockfile is canonical.
apm installfrom a lockfile is deterministic. CI must not need extra flags. - Failure mode is the product. Every error must name what failed, why, and one concrete next action. No stack traces in the default path.
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.
- 2d ago First seen · 106 lines · 53 tokens per session scan A 8310d130cca5
devx-ux-expert is an agent published in the GitHub repository microsoft/apm (3,668 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 1,342 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 2026-08-30.
Other agents, from other repositories
prompt-pipeline-runner
Executes the six-stage prompt-writer pipeline and produces two mandatory output artifacts (ready-to-run prompt, confidence report).
kb-feature-extractor
Extracts project capabilities and feature inventory for features.md from pre-filtered anchor-class files.
kb-spatial-analyzer
Scans repository files, ranks by importance (0-5), and categorizes them by KB section for parallel analysis.
project-documenter
Generates a digestible 3-tier/9-section birds-eye-view document from KB + codebase, with per-claim provenance in hidden HTML comments.
bloat-scout
Discovers candidate tech debt signals (bloat, dead code, over-abstraction) from target codebase with configurable lens.
kb-concept-extractor
Extracts domain concepts and terminology for conceptmap.md from pre-filtered files.