Chalk Labs
Need help deploying check?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/fransmankc-check
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/check
Tools it pre-approves 2
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Bash(mint*)
What's inside
- Skill name
check- Description
- Look up any Solana token by mint address. Use it when someone asks what a Solana token or coin is, who created it and where (pump.fun, Raydium LaunchLab, Meteora, Moonshot), its price or price history, all-time high, pools and liquidity, largest holders, mint or freeze authority, Token-2022 extensions, or risk signals. Read-only; reports facts and sources, never advice.
- License
- MIT
- Allowed tools
- Bash(mint, *)
- Instructions
- 50 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
Agent Skills spec issues
- name: missing
Files (1)
- SKILL.md
SKILL.md (first lines)
# mint: Solana token lookups
`mint <command> <mint>` prints one JSON object (`data`, `sources`, `missing`,
`partial`, `fetched_at`) and never interprets. You write the answer.
| Question | Run |
| --- | --- |
| What is it? Overall picture and risk signals | `mint risk <mint>` (runs the four below) |
| Supply, authorities, extensions, name | `mint overview <mint>` |
| Who made it, when, on which launchpad? | `mint origin <mint>` |
| Pools, liquidity, LP burned | `mint pools <mint>` |
| Largest holders, holder count | `mint holders <mint>` |
| Price over time, highs and lows | `mint history <mint> --interval 1h --limit 168` |
| Creator's other coins, did the creator sell? | `mint creator <mint>` |
| What usually happened to coins like this? | `mint outcomes <mint>` |
If the user typed `/mint:check` with an address ($ARGUMENTS), run
`mint risk $ARGUMENTS` and give a short, plain summary: what the token is,
where and when it was made, liquidity, holders, the signals found, and what
could not be checked. Add `mint history` only when price matters.
Read `${CLAUDE_PLUGIN_ROOT}/references/reading-results.md` before explaining
a field or a signal for the first time in a conversation.
## Wording rules
- Facts and signals only. Never say buy, sell, safe, scam, legit, or predict a
price. Do not rank or score the token.
- A signal is evidence, not a verdict. "The mint authority is revoked" does
not mean the token is safe. "Found" means the condition was seen, nothing more.
- Always give the mint address and the lookup time (`fetched_at`).
- Name the sources, and say plainly what is in `missing` and why.
- Never call `range_high` or `range_low` an all-time high or low unless
`covers_full_history` is `true`. Otherwise give the date range it covers.
## Use calls sparingly
- Run each command at most once per token per question. Reuse earlier output.
- Ask the user before looking up more than 3 tokens in one go.
- If a result says a budget or safety cap was hit, stop and tell the user.
Do not retry or loop. The budget resets within the hour.
## Keys
Never ask for a key, never accept one pasted into the conversation, and never
read the keys file. If a user offers a key, tell them to remove it from the
chat and use `/mint:setup` instead. Everything works without keys; a private
`SOLANA_RPC_URL` adds holder lists, because the public RPC refuses that call.From FransmanKC/mint, MIT.
More from FransmanKC/mint
- 0.549score
creator
FransmanKC
Track record of a Solana token's creator, with their other coins and what they did with this one.
SkillAFreshness: AClaude Code +9 - 0.549score
doctor
FransmanKC
Check mint's keys, data sources and this hour's call budget.
SkillAFreshness: AClaude Code +9 - 0.549score
holders
FransmanKC
Largest holders of a Solana token and their share of supply.
SkillAFreshness: AClaude Code +9 - 0.549score
outcomes
FransmanKC
What happened to coins like this one at 1, 7 and 30 days, with sample sizes.
SkillAFreshness: AClaude Code +9 - 0.546score
price
FransmanKC
Price history of a Solana token, with highs and lows.
SkillAFreshness: AClaude Code +9 - 0.546score
setup
FransmanKC
Add API keys or a private RPC URL for mint.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 15, 2026 (16 days ago)
- Last release
- Oct 15, 2026 (16 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/FransmanKC/mint
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from FransmanKC
- 0.549score
creator
FransmanKC
Track record of a Solana token's creator, with their other coins and what they did with this one.
SkillAFreshness: AClaude Code +9 - 0.549score
doctor
FransmanKC
Check mint's keys, data sources and this hour's call budget.
SkillAFreshness: AClaude Code +9 - 0.549score
holders
FransmanKC
Largest holders of a Solana token and their share of supply.
SkillAFreshness: AClaude Code +9 - 0.549score
outcomes
FransmanKC
What happened to coins like this one at 1, 7 and 30 days, with sample sizes.
SkillAFreshness: AClaude Code +9 - 0.546score
price
FransmanKC
Price history of a Solana token, with highs and lows.
SkillAFreshness: AClaude Code +9 - 0.546score
setup
FransmanKC
Add API keys or a private RPC URL for mint.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get check running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
check skill. Agent Mart. https://agentmart.dev/skills/fransmankc-check (last updated 2026-10-24)