Borrowing it
Nothing to install: this file belongs to coinbase/x402. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/coinbase/x402/main/.agents/skills/contributing/SKILL.mdgit clone --depth 1 https://github.com/coinbase/x402Wrote 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/coinbase/x402/contributing)<a href="https://agentmods.dev/skills/coinbase/x402/contributing"><img src="https://agentmods.dev/badge/skills/coinbase/x402/contributing/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/coinbase/x402/contributing"><img src="https://agentmods.dev/badge/skills/coinbase/x402/contributing.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 | $0.00052 | $0.00874 |
| Opus 5.5 | $0.00021 | $0.00350 |
| Sonnet 5.5 | $0.00010 | $0.00175 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
contributing 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 2d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contributing to x402
Reuse before writing new code
- Before writing anything, check in order whether the standard library (TS: ECMAScript and Node.js built-ins like
node:crypto; Python: the stdlib; Go: packages likenet/http,encoding/json,crypto), a native platform feature, or an already-installed dependency already does it; if so, use it. - Always reuse shared and core utilities.
- No new dependencies if it can be avoided.
Keep changes minimal
- Address a single issue per contribution, not multiple.
- Targeted edits, minimal diff, atomic commits.
- No abstractions or boilerplate that were not explicitly requested.
- No edits to legacy/v1 code; it is effectively frozen (security patches only). This includes the paths
typescript/packages/legacy/,go/legacy,python/legacyand thejava/SDK.
Code style
- Write clean, readable code (e.g. prefer guard clauses over nested conditionals, use descriptive names and small, single-purpose functions).
- Strong typing, avoid any weak types (
any,unknown, and their equivalents in other languages). Research the codebase to find the correct type, reuse existing type definitions rather than redeclaring them and confirm no type errors remain. - No overly defensive code or silent fallbacks.
- Apply DRY only where it reduces complexity; keep single-use logic inline rather than extracting a helper for it.
Comments
- Write comments that help a new reader understand the codebase.
- Never narrate in-progress work or describe code being replaced.
- Write onchain - never "on-chain" or "on chain".
- Don't change/remove existing comments, unless strictly needed due to code changes.
AI-assisted contributions
Follow the repository AI-assisted contribution policy in CONTRIBUTING.md. Review all AI-generated output before requesting maintainer review.
Working on an Issue
- Independently reproduce and verify the Issue first.
- When in doubt, ask clarifying questions on the Issue before writing code.
What ships with it
2 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.
- 2d ago First seen · 92 lines · 52 tokens per session scan A 16e6d643c986
contributing is a skill published in the GitHub repository coinbase/x402 (168 stars, last pushed 2d ago), licensed Apache-2.0. It adds 52 tokens to every session and 874 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other skills, from other repositories
gitlawb
Decentralized git for AI agents and humans. Use when the user wants to create repositories, push code, open pull requests, review and merge PRs, manage issues, create or claim bounties, delegate tasks to other agents, register human-readable names on Base L2, or interact with the gitlawb decentralized git network.…
git-flow
Git Workflow & Branching Strategy: Helps define and follow Git branching strategies (Git Flow, GitHub Flow, Trunk-Based), write good commit messages, manage releases, and resolve merge conflicts. Use whenever the user asks about Git workflow, branching strategy, commit conventions, release management, merge conflicts…
submit-hook
Submit a deployed Uniswap v4 hook to the public univ4-hooks registry - format the listing, open a PR (issue fallback) so it lists on the hook marketplace.
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
repo-sync
Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.