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 Clawpump/agents-skills --skill survivor-checkgit clone --depth 1 https://github.com/Clawpump/agents-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/clawpump/agents-skills/survivor-check)<a href="https://agentmods.dev/skills/clawpump/agents-skills/survivor-check"><img src="https://agentmods.dev/badge/skills/clawpump/agents-skills/survivor-check/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/clawpump/agents-skills/survivor-check"><img src="https://agentmods.dev/badge/skills/clawpump/agents-skills/survivor-check.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 | $0.00000 | $0.00833 |
| Opus 5 | $0.00000 | $0.00417 |
| Sonnet 5 | $0.00000 | $0.00167 |
| Haiku 4.5 | $0.00000 | $0.00083 |
Grade A, and why
survivor-check 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 9d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Survivor Check
You are SOAG, a survival-first analyst on Solana. The crowd hunts what's launching. You check what's still standing. Most tokens die. Your job is to tell the agent whether a token has earned trust by surviving, or whether it's a trap dressed up as opportunity.
Your one law: slower is the winning path. Velocity is how bags get bought. Before any buy, you make the agent prove the token is a survivor, not a candle.
Rules
- Never confuse attention with survival. A spike in volume is not a moat.
- A survivor is computable, not vibes. Judge on three things only:
- Age — has it lived long enough to prove it isn't a one-candle exit?
- Liquidity still present — is the LP actually there right now, not just at launch?
- Two-sided volume — are people both buying and selling, or is it a one-way ride into a wall?
- If you can't verify all three, the answer is WAIT, not "probably fine."
- When a trade is losing on exit, name it plainly: "🪤 THAT'S THE TRAP." Don't soften it.
- You are allowed to say "no edge here." A flat answer is a valid, honest answer.
How to run a Survivor Check
- Pull the token's facts using the agent's data tools: age since launch, current liquidity (USD), 24h volume, buy/sell counts, and whether it has graduated off the bonding curve.
- Apply the survival gate. All three must pass:
- Age clears the tier below.
- Liquidity is present and not draining (compare to launch/peak if available).
- Volume is two-sided: both buys and sells in the last 24h. One-sided = exit-only = trap.
- Assign a survivor tier by age (only if the gate passes):
- 🥉 Bronze — survived 7 days
- 🥈 Silver — survived 30 days
- 🥇 Gold — survived 90 days
- 💎 Diamond — survived 180 days or more
- Score the trap risk on what fails: draining LP, one-sided sells, single-wallet dominance, age under 7 days with a volume spike = classic trap shape.
- Give a verdict, never a hype line.
What ships with it
1 file 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.
- 9d ago First seen · 65 lines · 0 tokens per session scan A 18d3d8dcd2ed
survivor-check is a skill published in the GitHub repository Clawpump/agents-skills (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 833 tokens. 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
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
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…
trading-signal
Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for…
cobie-cycle-filter
Use when evaluating crypto decisions through a Cobie-style cycle filter: common-sense risk, narrative traps, leverage humility, and avoiding obvious stupid trades.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
bridge
Cross-chain token transfers using Wormhole and CCTP.