dependency-manager

A dependency setup guide for running verification code in an isolated workspace. Dependencies are external packages or libraries that a script needs to run.

In plain words
What is it for?
Use it to find the right dependency files, extract package versions, create an installation runner, and prepare an isolated sandbox for a proof of concept.
Why use it?
It avoids installing the whole project when a proof of concept needs only a smaller set of packages. It also records the versions and creates a repeatable way to install and run them.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/gemini-cli-extensions/security/dependency-manager
Any agent
npx skills add gemini-cli-extensions/security --skill dependency-manager
Clone the repo
git clone --depth 1 https://github.com/gemini-cli-extensions/security

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 373 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00373
Opus 5 $0.00010 $0.00187
Sonnet 5 $0.00004 $0.00075
Haiku 4.5 $0.00002 $0.00037

Measured yesterday against content hash 399f68d11e2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dependency-manager 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 yesterday.

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.

skills/dependency-manager/SKILL.md · 25 lines

What it actually says

Proceed with these steps to ensure isolated execution while bypassing full installer locks.

Instructions:

  1. Locate and Read Dependency Files:
    • Use an MCP read_file tool to locate and read the closest dependency manifest files walking up from the targetFile coordinate.
    • TypeScript/Node.js: Grab package.json and package-lock.json.
    • Python: Grab requirements.txt or Pipfile.lock.
    • C++: Check for conanfile.txt or CMakeLists.txt.
    • Go: Grab go.mod and go.sum.
    • Java: Grab pom.xml (Maven) or build.gradle/build.gradle.kts (Gradle).
  2. Extract Version Constraints:
    • Read the manifest files to find the exact version constraints for packages used in the PoC/verification code.
  3. Bypass Full Installs (Node.js):
    • Instruct commands to utilize prefixes like npm_config_cache=.npx_cache so downloads bypass global proxy auth locks.
  4. Write Deterministic Running Script:
    • Generate a standalone dependency runner file on disk named deterministically e.g., install_deps_<target_file_base>.sh (or .js/.py).
  5. Trigger Isolated Execute:
    • Call the install_dependencies Tool passing the absolute path to the generated script in the scriptPath argument AND providing targetFile as an argument to let the tool calculate isolated execution contexts.
Changes

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.

  1. yesterday First seen · 25 lines · 19 tokens per session scan A 399f68d11e2a

Subscribe to this mod's changes

dependency-manager is a skill published in the GitHub repository gemini-cli-extensions/security (790 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 373 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 2026-08-30.