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 geobrowser/geo-skills --skill geo-publishgit clone --depth 1 https://github.com/geobrowser/geo-skillsWrote 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/geobrowser/geo-skills/geo-publish)<a href="https://agentmods.dev/skills/geobrowser/geo-skills/geo-publish"><img src="https://agentmods.dev/badge/skills/geobrowser/geo-skills/geo-publish/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/geobrowser/geo-skills/geo-publish"><img src="https://agentmods.dev/badge/skills/geobrowser/geo-skills/geo-publish.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 | $0.00046 | $0.02780 |
| Opus 5 | $0.00023 | $0.01390 |
| Sonnet 5 | $0.00009 | $0.00556 |
| Haiku 4.5 | $0.00005 | $0.00278 |
Grade A, and why
geo-publish 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 12d 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Geo Knowledge Graph — Publishing
Publish testnet entities, relations, images, and edits with @geoprotocol/[email protected] and Contracts V2.
When to apply
Use this skill to:
- Create or update entities and relations.
- Delete a relation or delete an entity within one space.
- Publish an edit to a personal space.
- Propose, vote on, and execute an edit in a DAO space.
This skill is testnet-only and latest-only. Do not add an old-SDK or old-endpoint fallback.
Prerequisites
Shipped CLIs
The shipped bin/whoami.mjs and bin/publish-entity.mjs resolve dependencies from this skill directory. Install them once:
(cd <skill-dir> && bun install --frozen-lockfile)
Run them from the user's project with Node 20.6+ or Bun:
node --env-file=.env.geo-publish <skill-dir>/bin/whoami.mjs
node --env-file=.env.geo-publish <skill-dir>/bin/publish-entity.mjs --name "Ada Lovelace" --type PERSON_TYPE
Custom project scripts
Node ESM resolves packages from the script's project; it does not resolve them from an environment module-path override. A custom .mjs or .ts script must install its own exact SDK and direct viem dependency:
npm install --save-exact @geoprotocol/[email protected] [email protected]
# or: bun add --exact @geoprotocol/[email protected] [email protected]
Credentials
Use a dedicated, least-privilege testnet key. When the user does not have one configured, direct them to Export Wallet and tell them to press Copy key. Then ask them to put GEO_PRIVATE_KEY=0x... in .env.geo-publish, store it through a protected local or manual secret store, and add the env file to .gitignore.
- Ask the user to create the real env file in an editor or separate terminal you cannot see.
- Never paste or write the key in chat, command arguments, repository files, fork PR CI, build artifacts, or debug output.
- Never print the key, a secret-bearing URL, or an error that has not been redacted.
- Rotate the key immediately after actual or suspected exposure.
What ships with it
16 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.
- .gitignore 14 B
- bin/publish-entity.mjs 5.0 KB runs code
- bin/runtime.mjs 6.2 KB runs code
- bin/whoami.mjs 1.8 KB runs code
- bun.lock 5.7 KB
- examples/create-entity.md 3.8 KB
- examples/create-relation.md 3.2 KB
- examples/update-entity.md 2.2 KB
- package.json 452 B
- reference.md 16 KB
- test/cli.test.mjs 11 KB runs code
- test/docs-contract.test.mjs 5.4 KB runs code
- test/live-testnet-helpers.mjs 20 KB runs code
- test/live-testnet.test.mjs 7.1 KB runs code
- test/package-exports.test.mjs 1.2 KB runs code
- test/runtime.test.mjs 5.4 KB runs code
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.
- 12d ago First seen · 321 lines · 46 tokens per session scan A 4a6e9ff9edff
geo-publish is a skill published in the GitHub repository geobrowser/geo-skills (10 stars, last pushed 23d ago), licensed MIT. It adds 46 tokens to every session and 2,780 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 2026-08-31.
Other skills, from other repositories
signature-replay
Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.
official-sui-skills
Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…
bridge
Cross-chain token transfers using Wormhole and CCTP.
onchainkit
Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.
marginfi
MarginFi — Solana lending and borrowing.
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…