- Remove the robinhood-rejection guards in kol, smartmoney, signal and
cooking create-token so the CLI matches the backend, which now accepts
robinhood on these endpoints
- Update --chain / --dex / --raised-token help text and error messages
- cooking: robinhood launchpad uses trench / pons DEXes, native raised
token only
- Sync SKILL.md files, cli-usage.md and both Readmes with the new chain
support
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Address HackenProof report GMGNWM-143, where attacker-controlled token metadata
could hijack an AI agent driving gmgn-cli into executing an unauthorized trade.
Move guardrails from overridable SKILL.md text into code.
- Add src/sanitize.ts: neutralize prompt-injection framing and hidden/control
characters in API output (via printResult) and validate create-token metadata
- Add src/confirm.ts: code-enforced human confirmation for financial writes
(swap, multi-swap, order strategy create, cooking create) — reads a typed
"yes" from /dev/tty; automation requires GMGN_ALLOW_AUTOMATED_TRADES=1 + --yes
- Harden config.ts: tighten ~/.config/gmgn/.env to 0600 and warn if world-readable
- Update SKILL.md files, Readme.md and Readme.zh.md to document the gate,
the --yes flag, and untrusted-metadata handling
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Add gmgn-cli config --check: pure local check for GMGN_API_KEY, exit 0 = found, exit 1 = not found
- Update BEFORE RUNNING ANY COMMAND in all 6 SKILL.md files to use --check instead of file path detection
- Add fallback instruction for outdated gmgn-cli versions (unknown option → prompt user to npm install -g gmgn-cli)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- gmgn-cli config: add multi-language guidance (zh-CN/zh-TW/en) based on system locale
- gmgn-cli config --apply <key>: write GMGN_API_KEY + GMGN_PRIVATE_KEY to ~/.config/gmgn/.env and verify via track follow-wallet
- Delete skills/gmgn-config/SKILL.md — all logic now lives in CLI source
- Simplify BEFORE RUNNING ANY COMMAND in all 6 SKILL.md files to two CLI commands, no duplicated text
- Remove stale First-time setup sections (openssl-based) from all 6 SKILL.md files
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add skills/gmgn-config/SKILL.md with complete setup flow: key pair
generation, credential writing, and verification via track follow-wallet.
Verification result is output in the user's conversation language.
- Simplify all 6 SKILL.md BEFORE RUNNING ANY COMMAND to one line that
delegates to gmgn-config skill, removing duplicate logic.
- Remove locale detection from CLI — output only the link; Agent handles
all user-facing guidance in the conversation language.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Use node -e to write GMGN_API_KEY and GMGN_PRIVATE_KEY into .env —
node is guaranteed to be present since gmgn-cli requires Node.js.
Also clarify that the same config step applies when the user explicitly
runs gmgn-cli config and sends back an API Key.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replace awk+echo with python3+printf to correctly serialize the PEM
private key as a single-line \n-escaped value when writing to .env.
The awk approach produced multi-line output that broke .env parsing.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add a new `gmgn-cli config` command that automates Ed25519 key pair
generation for new users. The command reuses an existing keypair.pem if
present, or generates a new one, then outputs a pre-filled API Key
creation link with the public key embedded. Guidance text is output in
the user's system locale (zh-CN, zh-TW, or English).
All 6 SKILL.md files are updated with a BEFORE RUNNING ANY COMMAND
block that detects missing GMGN_API_KEY, triggers gmgn-cli config, and
instructs the Agent to write both GMGN_API_KEY and GMGN_PRIVATE_KEY
into ~/.config/gmgn/.env once the user provides their API Key.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Correct mkt_bps: it's the tax-recipient share (X handle in gift mode or
split_conf addresses in split mode), not a generic "marketing" fund
- Make twitter_account / split_conf conditional-required based on recipient_type
instead of always required
- Add two end-to-end Flap examples (split mode → BSC address, gift mode → X handle)
- Merge "Full worked examples" into the Usage Examples section
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The interval_seconds param is no longer used. Removed from the CLI
option, params assembly, CreateTokenParams, SKILL.md and cli-usage.md.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Update Readme.md, Readme.zh.md, src/commands/swap.ts and cooking.ts
with integer 0–100 slippage examples (e.g. 30 = 30%) to match the
updated API validation and skill docs.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Correct the --anti-mev-mode enum to off / normal / secure
(across cooking.ts, SKILL.md, cli-usage.md, and the TradeParam examples).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The pump_fee_share_list `provider` field rejected "wallet" with
"unknown provider: wallet". Valid values are solana / twitter / github.
- OpenApiClient: update PumpFeeShareInfo provider comment
- SKILL.md / cli-usage.md: provider enum solana / twitter / github,
username is a SOL address when provider = solana
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Address review feedback on PR #148: cooking stats uses exist auth
(authExistRequest), matching the CLI client and project terminology.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Shorten all 6 descriptions to 60-80 words with high-value terms in the
first 50 words (highest embedding weight). Add "crypto", "meme coin",
"meme token" where missing. Remove redundant chain-name repetition in
"Use when" sections. Keeps discriminating boundary hints (e.g. gmgn-track
→ gmgn-portfolio redirect for single-wallet queries).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Rewrite description fields across all 6 skills to follow a consistent
"Get [capabilities] via GMGN API. Use when user asks for [intents]."
pattern, aligned with how Openclaw agents search clawhub.ai. Adds
natural-language intent keywords (price, market cap, holder list,
Smart Money, KOL trades, copy-trading, etc.) so skills surface higher
in skill-search results.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replace top-level filled_input_amount/filled_output_amount with the
report object returned when state=30 and status=successful. Document
all report fields (amounts, tokens, decimals, price, gas) and update
order polling, post-swap receipt template, and cooking status polling
to reference report.input_amount / report.output_amount.
ClosesGMGNAI/gmgn-skills#34
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Rewrite Guided Launch Flow: required fields collected one at a time,
optional fields grouped into a single question for faster UX
- Add env lookup warning: document that a local .env in the workspace
overrides ~/.config/gmgn/.env, with a check command
- Redefine price_scale: profit_stop uses gain % from entry (e.g. "100" = +100% / 2×), loss_stop uses drop % from entry (e.g. "65" = drops 65%)
- Update all condition-order examples in SKILL.md and both READMEs accordingly
- Add is_anti_mev recommended note and anti-mev flag to swap examples
- Add order strategy create to Financial Risk Notice
- Fix response section heading format (bold → ###) for order strategy create/list
- Add reset_at field extraction guidance to Rate Limit Handling in all 6 skills
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
David Lau