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 hahahakang/onchain-narrative-research-skill --skill onchain-narrative-researchgit clone --depth 1 https://github.com/hahahakang/onchain-narrative-research-skillWrote 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/hahahakang/onchain-narrative-research-skill/onchain-narrative-research)<a href="https://agentmods.dev/skills/hahahakang/onchain-narrative-research-skill/onchain-narrative-research"><img src="https://agentmods.dev/badge/skills/hahahakang/onchain-narrative-research-skill/onchain-narrative-research/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/hahahakang/onchain-narrative-research-skill/onchain-narrative-research"><img src="https://agentmods.dev/badge/skills/hahahakang/onchain-narrative-research-skill/onchain-narrative-research.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 | $0.00085 | $0.01401 |
| Opus 5 | $0.00043 | $0.00700 |
| Sonnet 5 | $0.00017 | $0.00280 |
| Haiku 4.5 | $0.00009 | $0.00140 |
Grade A, and why
onchain-narrative-research 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 12d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onchain Narrative Research
Purpose
Turn a noisy crypto lead into a falsifiable research package:
- verify whether the lead has onchain substance;
- reconstruct what happened before, during, and after the trade/narrative;
- identify source accounts, projects, companies, people, and story catalysts;
- extract repeatable timing, liquidity, narrative, and execution signals;
- publish a report or update a reusable alpha-source knowledge base.
Prefer evidence over vibes. Treat screenshots and PnL calendars as leads, not proof.
Workflow
1. Frame The Lead
Capture the lead type:
- 晒单/PNL: screenshot, wallet address, win calendar, public claim.
- Token/trader: wallet, token contract, DEX/pump platform, transfer CSV.
- Narrative source: X post, founder statement, company announcement, meme, product launch.
- Entity source: person, company, lab, project lead, brand, celebrity.
- Category birth: first token in a new meme/topic/category, or early leader token.
Write the research question in one sentence, such as:
- "Is this trader's claimed profit visible in onchain cashflow?"
- "Which FDV/liquidity node did this trader actually make money from?"
- "What was the earliest public source of this token's story?"
- "Did a company/founder/person post cause a token cluster to launch?"
- "Which token was the first credible leader of this new category?"
2. Preserve Evidence
Save screenshots, URLs, wallet addresses, token contracts, timestamps, and exported CSVs. Use exact UTC timestamps when possible. Keep raw evidence separate from derived conclusions.
If the lead is modern/current, browse to verify live pages, links, and post timestamps. Prefer primary sources: block explorers, official project/company pages, the original X post, official docs, and raw onchain data.
3. Build The Data Layer
Choose the minimum data needed:
- Wallet-level ordinary transactions from block explorers.
- Token transfers and internal transactions.
- Transaction receipts/logs from RPC.
- DEX/pump-platform event logs.
- Token metadata: decimals, supply, symbol, name.
- Historical BNB/ETH/SOL price if converting to USD.
- Social/timeline data from original posts and downstream amplification.
What ships with it
4 files 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.
- 12d ago First seen · 168 lines · 85 tokens per session scan A 86cdb8d50375
onchain-narrative-research is a skill published in the GitHub repository hahahakang/onchain-narrative-research-skill (3 stars, last pushed 3mo ago), licensed MIT. It adds 85 tokens to every session and 1,401 once invoked, about $0.0004 per session on Opus 5. 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…
bridge
Cross-chain token transfers using Wormhole and CCTP.
onchainkit
Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.
marginfi
MarginFi — Solana lending and borrowing.
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…