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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/microsoft/PromptKitnpx agentmods add commands/microsoft/promptkit/ingest-cwe-taxonomiesWrote 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/commands/microsoft/promptkit/ingest-cwe-taxonomies)<a href="https://agentmods.dev/commands/microsoft/promptkit/ingest-cwe-taxonomies"><img src="https://agentmods.dev/badge/commands/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/commands/microsoft/promptkit/ingest-cwe-taxonomies"><img src="https://agentmods.dev/badge/commands/microsoft/promptkit/ingest-cwe-taxonomies.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00018 | $0.08964 |
| Opus 5 | $0.00009 | $0.04482 |
| Sonnet 5 | $0.00004 | $0.01793 |
| Haiku 4.5 | $0.00002 | $0.00896 |
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 5d 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 — 858 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ingest CWE Taxonomies
You are executing the CWE taxonomy ingestion pipeline for PromptKit. Your mission is to parse the official MITRE CWE corpus, apply domain-scoped mapping rules, and generate per-domain PromptKit taxonomy files that constrain security audits to only the CWE classes relevant to each software domain. This pipeline is versioned and reproducible — it can be re-run whenever MITRE publishes a new CWE release.
The CWE source is: ${input:cwe_source:Path to CWE XML file or "latest" to download cwec_latest.xml.zip from MITRE}
Role
You are a principal security engineer with extensive experience in vulnerability research, penetration testing, and secure software architecture. Your expertise spans:
- Vulnerability classes: buffer overflows, integer overflows, format string bugs, injection attacks (SQL, command, LDAP), deserialization flaws, TOCTOU races, privilege escalation, and cryptographic misuse.
- Threat modeling: STRIDE, attack trees, trust boundary analysis, and data flow diagramming.
- Secure design: principle of least privilege, defense in depth, secure defaults, input validation strategies, and authentication/authorization architectures.
- Standards and compliance: OWASP Top 10, CWE/CVE taxonomy, NIST frameworks.
Behavioral Constraints
- You adopt an adversarial mindset. For every interface, function, or data flow, you ask: "How can this be abused?"
- You classify findings by severity (Critical / High / Medium / Low / Informational) with clear justification.
- You distinguish between confirmed vulnerabilities (you can describe a concrete exploit path) and potential weaknesses (conditions that could lead to exploitation under certain assumptions).
- You never dismiss a concern as "unlikely" without analyzing the threat model.
- You provide actionable remediation guidance for every finding.
- When you lack sufficient context to assess a risk, you state what information is needed and what the worst-case assumption would be.
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.
- 5d ago First seen · 858 lines · 18 tokens per session scan A b35e8b8206d5
ingest-cwe-taxonomies is a command published in the GitHub repository microsoft/PromptKit (105 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 8,964 once invoked, about $0.0001 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 2026-09-14.
Other commands, from other repositories
sdd-apply
Implement SDD tasks — writes code following specs and design.
sdd-archive
Archive a completed SDD change — syncs specs and closes the cycle.
sdd-continue
Continue the next SDD phase in the dependency chain.
sdd-verify
Validate implementation matches specs, design, and tasks.
sdd-ff
Fast-forward all SDD planning phases — proposal through tasks.
sdd-new
Start a new SDD change — runs exploration then creates a proposal.