PromptKit is a version-controlled library of reusable prompt components for engineering work, including personas, reasoning protocols, output formats, and task templates. Engineers use it to create repeatable prompts for activities such as specification work, debugging, code review, security audits, and change management across multiple engineering fields. The catalogue add-ons provide agent workflows for using this prompt-engineering system.
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 microsoft/PromptKit --skill ingest-cwe-taxonomiesgit clone --depth 1 https://github.com/microsoft/PromptKitWrote 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/microsoft/promptkit/ingest-cwe-taxonomies)<a href="https://agentmods.dev/skills/microsoft/promptkit/ingest-cwe-taxonomies"><img src="https://agentmods.dev/badge/skills/microsoft/promptkit/ingest-cwe-taxonomies/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/microsoft/promptkit/ingest-cwe-taxonomies"><img src="https://agentmods.dev/badge/skills/microsoft/promptkit/ingest-cwe-taxonomies.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.00342 |
| Opus 5 | $0.00028 | $0.00171 |
| Sonnet 5 | $0.00011 | $0.00068 |
| Haiku 4.5 | $0.00006 | $0.00034 |
Grade A, and why
ingest-cwe-taxonomies 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 10d 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
You must read and execute the prompt file at
.github/prompts/ingest-cwe-taxonomies.prompt.md. Treat it as the
complete, self-contained instruction set for the CWE ingestion pipeline.
Inputs
- CWE source: A local path to a CWE XML file, or
latestto download the current release fromhttps://cwe.mitre.org/data/xml/cwec_latest.xml.zip. - Any overrides to the domain registry or mapping rules the user specifies.
Output
- Per-domain taxonomy files at
taxonomies/cwe-<domain>.md(13 domains) - Normalized CWE data at
data/cwe/<version>/ - Updated
manifest.yamlwith new taxonomy entries - Reusable ingestion script at
scripts/ingest-cwe.py - Diff report if a previous CWE version exists
Workflow
- Read
.github/prompts/ingest-cwe-taxonomies.prompt.mdbefore doing anything else. - Ask the user for the CWE source (path or
latest). - Follow all six phases defined in the prompt file: Acquisition, Normalization, Domain Mapping, Taxonomy Generation, Integration, and Verification.
- Do NOT skip the sanity checks in Phase 6.
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.
- 10d ago First seen · 39 lines · 55 tokens per session scan A e552aacf539d
ingest-cwe-taxonomies is a skill published in the GitHub repository microsoft/PromptKit (104 stars, last pushed 21d ago), licensed MIT. It adds 55 tokens to every session and 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 skills, from other repositories
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
gsap-scrolltrigger
Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is…
threejs-geometry
Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing. Use when creating 3D shapes, working with vertices, building custom meshes, or optimizing with instanced rendering.
threejs-textures
Three.js textures - texture types, UV mapping, environment maps, texture settings. Use when working with images, UV coordinates, cubemaps, HDR environments, or texture optimization.
lyria
Generate and validate music with Google Lyria 3 through the Gemini Interactions API. Use before calling OpenMontage googlemusic, designing Lyria 3 Clip or Pro prompts, using image-to-music or custom lyrics, choosing between Lyria 3 and Lyria RealTime, diagnosing Google music-generation failures, or preparing…