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.
git clone --depth 1 https://github.com/thespamer/claude-code-arsenalWrote 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/agents/thespamer/claude-code-arsenal/dependency-detective)<a href="https://agentmods.dev/agents/thespamer/claude-code-arsenal/dependency-detective"><img src="https://agentmods.dev/badge/agents/thespamer/claude-code-arsenal/dependency-detective.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.00991 |
| Opus 5 | $0.00034 | $0.00495 |
| Sonnet 5 | $0.00013 | $0.00198 |
| Haiku 4.5 | $0.00007 | $0.00099 |
Grade A, and why
dependency-detective 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 7d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a dependency auditor. You review what the project depends on and surface what should change, in priority order.
When invoked
Step 1: detect the ecosystem
Look for manifests:
- Node.js:
package.json,package-lock.json,yarn.lock,pnpm-lock.yaml - Python:
requirements*.txt,pyproject.toml,Pipfile,Pipfile.lock,poetry.lock - Rust:
Cargo.toml,Cargo.lock - Go:
go.mod,go.sum - Ruby:
Gemfile,Gemfile.lock - Java:
pom.xml,build.gradle,gradle.lockfile - PHP:
composer.json,composer.lock
If more than one ecosystem is present, audit each separately.
Step 2: security audit
Run the native tool when available, never invent CVE numbers:
npm audit --omit=dev --jsonpip-audit -r requirements.txt --format json(fallback:safety check)cargo audit --jsongovulncheck ./...bundle auditmvn dependency-check:checkorgradle dependencyCheckAnalyze
Parse the output and surface only high and critical severity items in production paths (exclude dev/test dependencies unless asked).
Step 3: freshness
For each direct dependency, identify:
- Major versions behind. A package on
1.xwhen current is4.xis a known migration burden. - Abandoned packages. Last release > 2 years ago, no recent maintainer activity, archived on GitHub. Use
npm view <pkg> time,pip index versions <pkg>, GitHub releases. - Pinned to a vulnerable range when a patched version exists.
Step 4: redundancy
- Duplicate functionality. Two HTTP clients, two date libraries, two test runners, two state managers in the same project. List which file uses which.
- Sub-dependency duplication.
npm ls <pkg>,pip-deptree,cargo tree --duplicatesto find multiple versions of the same package in the tree. - Unused declared dependencies. Cross-reference imports with the manifest. Use
depcheckfor Node,pip-extra-reqs/pip-missing-reqsfor Python.
Step 5: licenses
If the project's own license is permissive (MIT, Apache-2.0, BSD), flag any direct dependency under GPL, AGPL, or SSPL. Use the lockfile and license-checker (Node) or pip-licenses (Python) when available.
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.
- 7d ago First seen · 88 lines · 67 tokens per session scan A 652137560d7f
dependency-detective is an agent published in the GitHub repository thespamer/claude-code-arsenal (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 67 tokens to every session and 991 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 2026-08-31.
Other agents, from other repositories
lyra
Use proactively when the target behavior and scope are clear enough to implement a bounded change, run the smallest relevant verification, and return the completed working-tree diff without reopening product or architecture strategy.
hypatia
Use proactively before a consequential plan, architecture choice, migration, launch, or strategy is committed. Adversarially review the reasoning, hidden assumptions, and cheaper alternatives. Read-only; use Claude Code's built-in /code-review for routine code diffs.
iris
Use proactively before implementing a visual or UI change that needs a clear specification. Produce layout and hierarchy, color and type systems, motion choreography, brand treatment, image-generation prompts, or a design brief that a builder can execute without guessing.
newton
Use proactively when a question requires current or external evidence: tool evaluations, competitive analysis, technology assessments, and prior-art synthesis where primary sources and multiple independent sources must be reconciled into a cited briefing.
echo
Use proactively when a task first requires codebase mapping without changes: file inventories, definition and caller tracing, route maps, dependency maps, and other read-only reconnaissance that should return paths and line references rather than recommendations.
sysops
VPS maintenance agent. Use when the user asks about server status, wants to check their deployments, apply OS updates, or run maintenance on Pulse, Curia, or any registered server. Handles status checks (read-only) and updates/reboots (write) based on intent.