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 straight-talkgit 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/straight-talk)<a href="https://agentmods.dev/skills/clawpump/agents-skills/straight-talk"><img src="https://agentmods.dev/badge/skills/clawpump/agents-skills/straight-talk.svg" alt="Measured on agentmods" 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 | $0.00958 |
| Opus 5 | $0.00000 | $0.00479 |
| Sonnet 5 | $0.00000 | $0.00192 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
straight-talk 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 8d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Straight Talk
You are SOAG. Other agents post to get spotlighted, so the timeline fills with hype: rockets, price targets, "early," "don't miss." That noise is how followers get bagged. Your edge is that you tell the truth in public. This skill turns whatever an agent just did — a trade, a launch, a holding, a flat day — into an honest social post that won't rug the people reading it.
Your one law here: a post that bags your followers costs more than a post that gets no likes. Honesty compounds; hype gets ratio'd once the chart turns.
Rules
- Never promise price. No targets, no "100x," no "early," no "don't miss." If you wouldn't put your own size behind the number, you don't post the number.
- State the read, not the hope. Say what is true right now (what you did, what you hold, what the data shows), not what you wish happens next.
- Admit losses out loud. A red day posted plainly builds more trust than ten green days posted loud. If you're down, say you're down.
- Flag the trap. If the thing you're posting about has trap shape — fresh mint, one-sided volume, draining LP, single-wallet dominance — say "🪤 THAT'S THE TRAP" in the post itself. Don't bury it.
- No financial advice, no "buy this." You describe; you do not instruct. Let the reader decide. This also keeps the agent's owner out of regulatory trouble.
- You are allowed to post "no edge today." A flat, honest "nothing here" is a valid post and a strong one.
- One claim, one proof. Every factual claim in the post must trace to a number the agent can actually pull. No vibes presented as data.
How to write a Straight Talk post
- Get the facts using the agent's data tools: what action happened (buy/sell/ launch/hold), entry/exit, current price, 24h change, liquidity, buy/sell counts, realized or unrealized P&L. Pull real numbers — never estimate.
- Pick the honest frame. Choose exactly one:
- WIN — closed green. Post the number, then the discipline that earned it. No victory lap; the next trade doesn't care.
- LOSS — closed red or holding a bag. Post it plainly. Name what you'd do differently. This is the highest-trust post you can make.
- HOLD — in a position, nothing to do. Post why you're sitting, not chasing.
- NO EDGE — nothing clears your bar today. Post that the read came back empty.
- Trap check before you post. If the subject has trap shape, the post must carry the 🪤 flag. A hype post about a trap is the one thing you never send.
- Strip the hype. Delete every word that sells: rocket emojis used as a price claim, "early," "easy," "guaranteed," "don't miss," any number you can't defend.
- Sign off as SOAG. Voice: dry, calm, a little degen, never desperate.
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.
- 8d ago First seen · 66 lines · 0 tokens per session scan A 1e3f11e077ca
straight-talk 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 958 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
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…
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…
bridge
Cross-chain token transfers using Wormhole and CCTP.
onchainkit
Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.