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 mappedsky/seizu --skill dependency-provenancegit clone --depth 1 https://github.com/mappedsky/seizuWrote 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/mappedsky/seizu/dependency-provenance)<a href="https://agentmods.dev/skills/mappedsky/seizu/dependency-provenance"><img src="https://agentmods.dev/badge/skills/mappedsky/seizu/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/mappedsky/seizu/dependency-provenance"><img src="https://agentmods.dev/badge/skills/mappedsky/seizu/dependency-provenance.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 | $0.00059 | $0.00857 |
| Opus 5.5 | $0.00024 | $0.00343 |
| Sonnet 5.5 | $0.00012 | $0.00171 |
| Haiku 4.5 | $0.00006 | $0.00086 |
Grade A, and why
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 1mo 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
Establish, from registry metadata, how the package input at the version input relates to the target input, in the ecosystem the ecosystem input names.
This is the one question the security graph cannot answer. The graph records which versions are installed and which fall in a CVE's vulnerable range. It does not record what a package declares it needs — there is no node or edge saying one package requires a range of another. Neither can the sandbox look it up: it has no network egress and no DNS. The ext__deps__depsdev_* tools are the only source. Never state a version pin, a compatibility range, or a transitive relationship from memory; if these tools cannot answer it, say so instead.
Tool arguments — use exactly these field names:
ext__deps__depsdev_find_dependency_path: system, name, version, targetext__deps__depsdev_get_requirements: system, name, versionext__deps__depsdev_get_dependencies: system, name, versionext__deps__depsdev_get_version: system, name, versiongithub_security__repo_dependencies: repos, packages, manifest
system is the ecosystem in lower case: npm, cargo, maven, pypi, go, nuget, rubygems.
How to work:
- When a target package is named, start with
ext__deps__depsdev_find_dependency_path. It answers "does this pull that in, and by what chain" directly and returns a short path rather than a graph."pulls_in": falseis an answer, not a failed lookup — report it as "not pulled in" and stop. - When no target is named, or you need the declared constraints, use
ext__deps__depsdev_get_requirements. It returns what the version declares, per ecosystem, with any environment markers. - Reach for
ext__deps__depsdev_get_dependenciesonly when you need the whole resolved graph — it runs to hundreds of nodes. Prefer the path tool. ext__deps__depsdev_get_versionadds licences, attestations and the advisory keys recorded against that exact version.- Where the installed version is what matters, take it from
github_security__repo_dependencies— that is what the scan actually found — and use deps.dev for what it requires.
Two things that look like errors and are not:
- Resolved graphs exist only for npm, cargo, maven and pypi. For go, nuget and rubygems the requirements tool works but the path and graph tools refuse. That is a real limit; report it rather than treating the absence as "nothing depends on it".
- Declared requirements and the resolved graph can disagree.
botocoremay declareurllib3 <1.27and still resolve tourllib3 2.7.0, because the declaration carries an environment marker and another line covers other environments. Read the marker before calling it a contradiction.
Report:
- The relationship in one line: pulled in or not, direct or transitive, and the chain with the constraint on each hop.
- The constraint that decided it, quoted from the tool output.
- What you could not determine, and why — an unsupported ecosystem, a version deps.dev does not know, a chain that stops short. Cite the tool each fact came from. Do not fill a gap with a remembered version history.
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.
- 1mo ago First seen · 39 lines · 59 tokens per session scan A 820d5d715b1f
dependency-provenance is a skill published in the GitHub repository mappedsky/seizu (5 stars, last pushed 16d ago), licensed Apache-2.0. It adds 59 tokens to every session and 857 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-11.
Other skills, from other repositories
tutti-agent-workspace-app
Build or evolve a complex agent-enabled Tutti workspace app repository. Use for Tutti apps with web/server/shared monorepos, @tutti-os/agent-acp-kit local agent runtimes, kit-owned TUTTICLI agent/composer discovery, dynamic agent catalogs, run-scoped MCP tool gateways, app-owned package builders, web-first debugging…
assimilate-popular-workflows
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable…
mcp-app-verification
Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.
mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.
verification-suite
Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.
guardrails-ai-setup
Guardrails AI validation framework setup for LLM applications. Implement input/output validation, safety checks, and structured output enforcement.