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 athola/claude-night-market --skill dependency-verificationgit clone --depth 1 https://github.com/athola/claude-night-marketWrote 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/athola/claude-night-market/dependency-verification)<a href="https://agentmods.dev/skills/athola/claude-night-market/dependency-verification"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/dependency-verification/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/athola/claude-night-market/dependency-verification"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/dependency-verification.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 | $0.00033 | $0.01333 |
| Opus 5.5 | $0.00013 | $0.00533 |
| Sonnet 5.5 | $0.00007 | $0.00267 |
| Haiku 4.5 | $0.00003 | $0.00133 |
Grade A, and why
dependency-verification 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.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A package name the model produced is a claim, not a fact. The registry is the fact. Verify before you install.
Dependency Verification
Overview
Code-generating language models recommend packages that do not
exist at a measured rate of 5.2% (commercial models) to 21.7%
(open models) across 576,000 samples (Spracklen et al. 2024,
arXiv 2406.10279). Worse, 58% of hallucinated names recur across
reruns, so an attacker can predict them, register the empty name,
and ship malware. This is "slopsquatting." A proof-of-concept
package (huggingface-cli) drew over 30,000 downloads after being
registered against a commonly hallucinated name. Package
hallucination is also inversely correlated with coding-benchmark
score, so a better model does not make this go away.
The defense is cheap: confirm the name exists in its registry
before installing or recommending it. This skill defines that
check and is enforced by the guard_package_hallucination.py
PreToolUse hook.
When To Use
Apply before any of these:
- Running
pip install,uv add,npm install,pnpm add,yarn add,cargo add,poetry add, orpdm add. - Writing a dependency into
pyproject.toml,requirements.txt,package.json, orCargo.toml. - Recommending a package to the user in prose.
When NOT To Use
- Bumping versions of packages already known to exist (use
sanctum:version-updates) - Auditing a dependency's supply chain (use
leyline:supply-chain-advisory)
The Two Signals
A package fails verification on either signal:
- Nonexistent: the name is absent from its registry. This is a likely hallucination. Do not install it. Search for the correct name or confirm the package was renamed or removed.
- Typosquat / slopsquat: the name is one or two edits from a
popular package (for example
reqeustsversusrequests). This is either a typo or a deliberate impersonation. Confirm the exact name you intend before proceeding.
A name that is unknown to the bundled popular-package set but
present in the registry passes. A name that cannot be checked
because the registry is unreachable is reported as unverified,
never blocked: the guard does not fail closed on a network error.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 150 lines · 33 tokens per session scan A 0756f5bb8aa9
dependency-verification is a skill published in the GitHub repository athola/claude-night-market (342 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 1,333 once invoked, about $0.0001 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 2026-09-18.
Other skills, from other repositories
supply-chain-security-expert
Secure the path from dependency to deployed artefact: SBOMs, dependency scanning, build provenance, artefact signing and CI/CD integrity. Use when the user mentions supply chain security, SBOM, CycloneDX or SPDX, SCA or dependency scanning, Sigstore or cosign, SLSA, provenance and attestation, a compromised or…
apply-contagion-risk-mapping
Use when assessing organizational risk exposure — to map how cascade failures propagate through implicit network proximity, shared infrastructure, and correlated dependencies, because organizations that assess only direct relationships systematically underestimate their exposure to others' failures.
ai-hallucination-fact-check-protocol
Design a fact-checking protocol for AI-generated text, extending SIFT with AI-specific adaptations for hallucination detection. Use when students need to verify AI claims and citations.
dependency-review
Evaluate a new dependency before adding it. Invoke when anyone proposes npm install, pip install, cargo add, or go get for a new package.
artifact-verifier
Verify that declared deliverable files exist, are non-empty, remain inside an allowed root, and avoid declared placeholder terms.
verification-bench
Run a labeled fixture set through the bundled deterministic subject and report catch rate and false-refusal rate without converting synthetic performance into production proof.