lilith-zero: Skill for Claude Code

.agent/skills/google_oss_management/SKILL.md

google_oss_management is a skill for Claude Code, Codex from BadC-mpany/lilith-zero. It costs 36 tokens per session (1,141 once invoked), scanned A, original, Apache-2.0.

A project-specific release and contribution policy for the Lilith open-source project. It requires specified continuous-integration checks—automated checks that build, lint, and test code—before committing or releasing.

In plain words
What is it for?
Handling commits, pushes, releases, CI workflow changes, build configuration changes, and changelog updates while following Lilith's required verification commands.
Why use it?
It prevents code from being committed based on assumption instead of evidence that the project's required checks passed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is BadC-mpany/lilith-zero's own configuration. It tells Claude Code and Codex how to work on lilith-zero itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lilith-zero configures →

Reuse

Borrowing it

Nothing to install: this file belongs to BadC-mpany/lilith-zero. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/BadC-mpany/lilith-zero/main/.agent/skills/google_oss_management/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/BadC-mpany/lilith-zero

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for google_oss_management

README.md
[![agentmods](https://agentmods.dev/badge/skills/badc-mpany/lilith-zero/google_oss_management.svg)](https://agentmods.dev/skills/badc-mpany/lilith-zero/google_oss_management)
Your own site
<a href="https://agentmods.dev/skills/badc-mpany/lilith-zero/google_oss_management"><img src="https://agentmods.dev/badge/skills/badc-mpany/lilith-zero/google_oss_management.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,141 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 5.1 $0.00036 $0.01141
Opus 5 $0.00018 $0.00571
Sonnet 5 $0.00007 $0.00228
Haiku 4.5 $0.00004 $0.00114

Measured 6d ago against content hash 553983307ce4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

google_oss_management 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 6d 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.

.agent/skills/google_oss_management/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google-Grade Open Source Project Management (Lilith Edition)

This skill enforces strict engineering rigor for the Lilith project. It mandates that no code is committed without passing the specific CI workflows defined in .github/workflows/ci.yml.

When to use this skill

  • Ready to Commit: When the user wants to commit changes, push code, or release a new version.
  • Workflow Updates: When the user modifies .github/workflows/ci.yml or build configurations (lilith-zero/Cargo.toml, sdk/pyproject.toml).
  • Documentation: When generating CHANGELOG.md updates based on recent diffs.
  • Quality Gate: When requested to "finalize" or "polish" a feature for merging.

How to use it

1. Pre-Commit Workflow Validation (The "Green Build" Rule)

Before generating any commit messages, you MUST ask the user to run the relevant verification commands. Do not assume pass.

A. Rust Core Changes (lilith-zero/)

If changes touch lilith-zero/src, lilith-zero/Cargo.toml, or lilith-zero/tests:

  1. Format & Lint:
    • cd lilith-zero; cargo fmt --all -- --check
    • cd lilith-zero; cargo clippy --all-targets --all-features -- -D warnings
  2. Test:
    • cd lilith-zero; cargo test --all-features
  3. Audit (Optional):
    • cd lilith-zero; cargo audit
B. Python SDK Changes (sdk/)

If changes touch sdk/, sdk/src, or pyproject.toml:

  1. Lint:
    • ruff check sdk/src/lilith_zero sdk/tests
  2. Type Check:
    • mypy sdk/src/lilith_zero --strict --ignore-missing-imports
  3. Test:
    • cd sdk; python -m pytest tests -v
C. Integration/Full System

If changes affect the interaction between Rust and Python:

  1. Build Rust Binary:
    • cd lilith-zero; cargo build --release
    • Note: Set env var: export LILITH_ZERO_BINARY_PATH="lilith-zero/target/release/lilith-zero"
  2. Run Integration Test:
  3. Sandbox Verification:
    • cd lilith-zero; cargo run --example sandbox_check

Read the full file on GitHub · 89 lines

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. 6d ago First seen · 89 lines · 36 tokens per session scan A 553983307ce4

Subscribe to this mod's changes

google_oss_management is a skill published in the GitHub repository BadC-mpany/lilith-zero (23 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,141 once invoked, about $0.0002 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.