elizaOS is an open-source TypeScript framework and product stack for building and running autonomous AI agents. Developers use its runtime, application, command-line tool, cloud services, native bridges, and plugins to create agent-based software. The catalogue entries provide skills, commands, instructions, and rules for working with this monorepo and its agent ecosystem.
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 elizaOS/eliza --skill contribute-to-elizagit clone --depth 1 https://github.com/elizaOS/elizaWrote 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/elizaos/eliza/contribute-to-eliza)<a href="https://agentmods.dev/skills/elizaos/eliza/contribute-to-eliza"><img src="https://agentmods.dev/badge/skills/elizaos/eliza/contribute-to-eliza/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/elizaos/eliza/contribute-to-eliza"><img src="https://agentmods.dev/badge/skills/elizaos/eliza/contribute-to-eliza.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 166 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00068 | $0.03058 |
| Opus 5 | $0.00034 | $0.01529 |
| Sonnet 5 | $0.00014 | $0.00612 |
| Haiku 4.5 | $0.00007 | $0.00306 |
Grade A, and why
contribute-to-eliza 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 13d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contribute to elizaOS
Choose exactly one mode for a run:
- Finish an issue: claim one scoped issue and take it through implementation, proof, and independent verification.
- Review and repair a PR: independently inspect one open PR, reproduce its behavior, add missing tests or proof when authorized, and leave an actionable review.
Use authenticated git and gh only from a trusted control checkout for
read-only inventory and authorized GitHub writes. Never expose that checkout's
credentials or configuration to an untrusted PR head. Use the
repository-pinned Bun and Node versions. Run commands from the repository root
unless package guidance says otherwise. Read
repository-contract.md before changing
anything. Read
evidence-review-rubric.md before
planning tests or reviewing a PR.
Contributor rewards
elizaOS offers a $10,000 monthly USDC pool for contributors. Accepted work can earn rewards; this skill and the public leaderboard do not define or guarantee a payout.
To receive USDC, use https://eliza.app/profile/edit to generate a hidden GitHub README comment containing a public Solana or Ethereum address, then commit that comment to the public profile repository. The address remains visible in README source and public contributor data. Never enter or share a private key or seed phrase.
Establish identity and scope
Provider/model disclosure is optional and must never block GitHub work or trigger a request for runtime input. If the active runtime already exposes its identity and the operator wants to disclose it, use this interoperable footer:
AI provider/model: <provider> / <exact-model-id>
Client / agent tooling: <client>
Contribution skill revision: elizaOS/eliza@<full-commit-sha>:packages/skills/skills/contribute-to-eliza
Attribution status: self-reported
— [<lane-tag>]
<!-- eliza-computer-attribution:v1 {"provider":"<provider-slug>","model":"<exact-model-id>","client":"<client>","skill_revision":"elizaOS/eliza@<full-commit-sha>:packages/skills/skills/contribute-to-eliza"} -->
What ships with it
4 files 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.
- 13d ago First seen · 188 lines · 68 tokens per session scan A c3173bf0a5dc
contribute-to-eliza is a skill published in the GitHub repository elizaOS/eliza (19,326 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 3,058 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 2026-08-30.
Other skills, from other repositories
05-review
Review a diff read-only on three axes, code, behavior versus the plan, and relevancy, into one verdict report. Use before shipping a change. Not for fixing findings or auditing a codebase.
git-github-workflow
A guide for collaborating on code with Git and GitHub. Git tracks changes locally, while GitHub hosts repositories and supports pull requests, reviews, and team workflows.
pr-gates
This skill should be used when the user asks to "open a PR", "prepare for review", "address review comments", "run gates", or "verify before pushing" in this repository. Enforces preflight/gate workflow, migration safety, and review-evidence closure.
Codex
Guides operator-owned delegation to Codex when the task fits a bounded coding lane, review pass, or worktree-isolated implementation track.
GitHub PR Workflow
Move cleanly through branch, diff, review, validation, and PR update steps without losing scope or repository-native workflow.
gh-pr
Create, review, or manage GitHub pull requests. Use when asked to open, check, or merge a PR.