Missed one stale "sol / bsc only" reference in the Parameters section;
signal supports sol / bsc / robinhood.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- 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>
Adds a new skill that scores any wallet address across three angles —
profitability (track-record score), copy-tradeability (score + a
latency/slippage/gas backtest), and Dev reputation for token-creator
wallets — plus trading-style tags, computed deterministically from
GMGN portfolio data. Wires it into CLAUDE.md's skill routing and the
Readme skill tables/install instructions, and refreshes the stale
plugin metadata descriptions/keywords to reflect all 8 current skills.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
- Fix output appearing twice by clarifying Output Rule in SKILL.md
- Simplify entry cost batch detail: replace per-wallet lists with
selling/accumulating counts on the batch summary line
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Give operators/agents visibility into when the CLI neutralizes suspicious token
metadata in an API response.
- sanitizeForOutputWithCount returns the cleaned value plus the number of altered
strings; sanitizeForOutput kept as a thin wrapper
- printResult prints "[gmgn-cli] Notice: neutralized N suspicious metadata value(s)"
to stderr when anything was filtered (extra detail under GMGN_DEBUG); sanitized
JSON still goes to stdout so piping is unaffected
- document the notice in the gmgn-token SKILL untrusted-data warning
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>
Two improvements:
1. Extract 700-line inline Python script to analyze.py — Claude no longer
streams the entire script as text, reducing response time from ~2min to
~5s (API calls take ~3s, script execution <1s).
Also adds full 3-way concurrency: holders + dev fetched in parallel, then
created-tokens fires immediately when dev result arrives — saving ~1.2s vs
prior serial approach. EVM addresses auto-detect chain (bsc→eth→base).
2. Add Output Rule section after the run command — Claude's reply MUST contain
only the raw stdout verbatim, no summary or omission. Previously the CRITICAL
note appeared before the command, so it was forgotten by reply time; moving
it after (as the last thing Claude reads before replying) enforces compliance.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
New skill for analyzing token holder chip structure.
Includes dump risk, dev wallet status, related funds,
quality signals, entry cost batches, buying power,
and AI recommendation. Supports zh/en bilingual output
via LANG env var. Uses pure Python subprocess + ThreadPoolExecutor,
no /tmp files.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Complements the robinhood config: buildTrenchesBody now only sends
launchpad_platform / quote_address_type when non-empty. These fields are
allow-list filters, so an empty array returned an all-empty response. A
future chain missing from the config maps now degrades to API defaults
instead of silently returning nothing (chains should still be added to
both maps).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
market trenches returned all-empty on robinhood because
TRENCHES_PLATFORMS and TRENCHES_QUOTE_ADDRESS_TYPES had no robinhood
entry, so an empty quote_address_type filtered out every result.
Add robinhood config:
- platforms: noxa, virtuals_v2, bankr, dyorswap, pool_uniswap_v2/v3/v4
- quote_address_type: [11, 20, 24, 12, 0]
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Update hot-searches default-set docs from 4 chains to 5
(sol/bsc/base/eth/robinhood) and fix two stale "7-chain" leftovers.
- skills/gmgn-market/SKILL.md, docs/cli-usage.md: 5-chain default
- src/commands/market.ts: update default-config comment
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Add robinhood as a supported chain across the CLI and skills, and stop
advertising chains that are not publicly supported yet.
robinhood:
- validate.ts: add to VALID_CHAINS and treat as EVM for address checks
- reject guards for commands that do not support it: track kol,
track smartmoney, cooking create (mirrors market signal)
- --chain help updated for supported commands (token/portfolio/swap/
market kline·trending·trenches·hot-searches/track follow-*/order get/
gas-price); OpenApiClient chain comment
- docs: all SKILL.md, Readme.md, Readme.zh.md (split-out row for
unsupported commands), cli-usage.md, plugin/marketplace descriptions
disable monad/megaeth/hyperevm/tron:
- comment monad out of VALID_CHAINS (kept for quick re-enable)
- strip these chains from all --chain help, SKILL.md, cli-usage.md
(hot-searches default now 4 chains: sol/bsc/base/eth)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Add --min-*/--max-* range flags to `market hot-searches` (same metric names as
market trending); flatten filter fields onto each param (no nested filter object)
- Document response as long-form RankItem fields (server maps shortcodes); drop the
filter_id field from the documented response shape
- Sync SKILL.md, cli-usage.md, Readme.md, Readme.zh.md, and OpenApiClient types
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 exact fixed messages for link guidance and verification results in
zh-CN, zh-TW, and English. Instruct Agent to output them verbatim in
the user's conversation language without paraphrasing.
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>
ETH trenches/trending (SKILL.md, cli-usage.md):
- Add per-chain --launchpad-platform value tables incl. ETH for `market trenches`
- Add ETH trenches usage examples (all / new_creation / completed)
- Rename "Trending — ETH (No Platform Filter)" to "Trending — ETH by Launchpad
Platform" and add --platform ETH examples (platform list is now supported)
min_created/max_created units (market trending):
- Clarify that the raw upstream rank interface accepts minutes only; the
openapi-service does NOT forward this field — it evaluates the age window itself
(cutoff = now - duration, native for m/h/d), so 6h/7d work via this CLI.
- Note a bare number with no unit suffix is rejected. Update --help text and
code comment accordingly.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Register dynamic --min-*/--max-* flags on `market trending`, mirroring the
trenches pattern; forwarded as min_<metric>/max_<metric> query params to
/v1/market/rank
- Add RANK_RANGE_FIELDS covering the 18 numeric metrics plus min/max-created
token-age windows (m/h/d duration strings, passed through as-is)
- Document range filters and web-client filter aliases in SKILL.md, cli-usage.md,
Readme.md and Readme.zh.md
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
GMGN.AI