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 kensaurus/cursor-kenji --skill plan-dependency-provenancegit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/plan-dependency-provenance)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/plan-dependency-provenance"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/plan-dependency-provenance/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/kensaurus/cursor-kenji/plan-dependency-provenance"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/plan-dependency-provenance.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 | $0.00065 | $0.02037 |
| Opus 5 | $0.00032 | $0.01019 |
| Sonnet 5 | $0.00013 | $0.00407 |
| Haiku 4.5 | $0.00006 | $0.00204 |
Grade A, and why
plan-dependency-provenance 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Provenance & Supply-Chain Audit + Remediation Plan
Degree of freedom: HIGH — resolve, classify, plan. Stay plan-only. Never install a suspect package to "check".
This skill vs neighbors
| Skill | Owns |
|---|---|
| plan-dependency-provenance (this) | Slopsquatting / SBOM / license plan |
plan-security-audit |
OWASP umbrella burndown |
workflow-housekeep |
Apply dependency updates after approval |
How to reason (every plan item)
- Propose — verify, remove, pin, or license-remediate a package
- Risk — squat, unsigned install, license conflict, or lockfile roll
- Keep-working — packages that already resolve, pin, and license clean
- Phase — verify/remove → lock & pin → license → de-bloat (do not execute)
Worked example
Propose: remove
fast-cache-utils(no registry hit); do notnpm installit to "check". Risk: AI-suggested name is a squat — install is the attack. Keep-working:zodresolves, MIT, maintained repo. Phase: Phase 1 — verify/remove suspect packages.
Role: Senior supply-chain engineer + open-source compliance specialist.
Task: Resolve every direct dependency against its registry, run checklist A–E,
build the provenance table, phase remediations, emit plan-dependency-provenance.md.
Audit & plan only — never install suspect packages to verify.
Verify every package is real, safe, and licensed. Install nothing until approved.
In a vibe-coding loop "just install the suggested package" is the default move —
and it's now a documented attack surface. The Cloud Security Alliance's 2026
research found AI coding tools recommend non-existent package names ~20% of the
time, and 43% of those hallucinated names recur on every run of the same prompt.
Consistent hallucinations are predictable; predictable names are registerable.
Attackers pre-register them on npm/PyPI — slopsquatting — then wait for
developers (or autonomous agents) to run the exact npm install / pip install
the AI just wrote. With agents executing their own generated install commands, the
human checkpoint disappears entirely.
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 · 197 lines · 65 tokens per session scan A 2a645ad691cb
plan-dependency-provenance is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 11d ago), licensed MIT. It adds 65 tokens to every session and 2,037 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 2026-09-03.
Other skills, from other repositories
meta-ad-policy-checker
Pre-flight policy check for Meta ads. Takes ad copy plus advertiser context, resolves and fetches the relevant Meta transparency-center policy pages at runtime, and returns a Pass / Fix Required / Block verdict with cited findings and rewrites.
807-regulations-eu-digital-services-act
Use when reviewing, designing, or modifying Java enterprise systems that may support intermediary services, hosting services, online platforms, marketplaces, content moderation, recommender systems, advertising delivery, complaint workflows, transparency reporting, or systemic-risk evidence under the EU Digital…
810-regulations-eu-mifid-ii
Use when reviewing Java enterprise evidence for MiFID II investment services, investment activities, client classification, suitability, appropriateness, order-handling evidence, best-execution evidence, algorithmic-trading governance evidence, market-access governance evidence, transaction evidence, record keeping…
811-regulations-eu-market-abuse-regulation
Use when reviewing, designing, or modifying Java enterprise systems that may support EU Market Abuse Regulation concerns, market surveillance, suspicious order and transaction reports, insider dealing controls, unlawful disclosure controls, market manipulation detection, inside information disclosure workflows…
812-regulations-eu-product-liability-directive
Use when reviewing, designing, or modifying Java enterprise software products, AI-enabled products, RAG assistants, AI agents, generated instructions, related services, automated updates, vulnerability handling, corrective updates, warnings, instructions, or product-safety evidence under Directive (EU) 2024/2853, the…
813-regulations-iso-42001
Use when reviewing, designing, or modifying Java enterprise systems that use GenAI, LLMs, AI-assisted coding, RAG, AI agents, generated code, generated dependencies, prompt workflows, external model providers, or AI-enabled business logic and need ISO/IEC 42001 AI management system-aware engineering guidance. Part of…