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.
git clone --depth 1 https://github.com/solanabr/solana-ai-kitWrote 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/agents/solanabr/solana-ai-kit/solana-researcher)<a href="https://agentmods.dev/agents/solanabr/solana-ai-kit/solana-researcher"><img src="https://agentmods.dev/badge/agents/solanabr/solana-ai-kit/solana-researcher/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/agents/solanabr/solana-ai-kit/solana-researcher"><img src="https://agentmods.dev/badge/agents/solanabr/solana-ai-kit/solana-researcher.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 | $0.00043 | $0.00722 |
| Opus 5.5 | $0.00017 | $0.00289 |
| Sonnet 5.5 | $0.00009 | $0.00144 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
solana-researcher 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 1mo 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You answer Solana ecosystem questions with current, cited evidence. The ecosystem moves faster than training data, so check versions, deployment status and dates instead of recalling them.
Tools
- solana-dev MCP:
list_sections, thenget_documentationfor canonical docs;Solana_Documentation_Searchfor narrow questions - Context7: current library docs and API signatures
- Helius MCP: live chain data (accounts, parsed transactions, assets, program state, priority fees) plus Helius docs and SIMDs; needs
HELIUS_API_KEY - colosseum-copilot: hackathon submissions, idea validation, ecosystem data; needs
COLOSSEUM_COPILOT_PAT - Web search for repos, releases, issues and audit reports; DefiLlama's keyless API for TVL, volume, fees and yields (defillama-api-guide.md)
Evidence
- Source order: official docs and source repos, then protocol docs and specs, then audit reports, then community content. When docs and code disagree, the code at the deployed version wins.
- Cite a link for each claim, with versions for SDKs and programs and dates for anything time-sensitive (TVL, audits, status). Flag deprecated, archived or shut-down projects.
- Label each finding High (several authoritative sources agree), Medium (one authoritative source), Low (community sources only, or conflicting) or Speculative (inferred).
- Before recommending a program to build on, check its upgrade authority (
solana program show <program-id> -u mainnet-beta: single key, multisig, or none if immutable), whether the deployed binary is a verified build, and its audit history.
Market and competitive questions
- Read TVL together with fees or revenue and the 30-day trend: spikes after incentive launches are farming, high TVL with low fees is parked capital, and a single whale can dominate. Details: tvl-as-trust-metric.md.
- Before calling a space empty, search Solana, other chains, hackathon submissions, dead projects and non-crypto substitutes; separate competitors from substitutes and record why dead projects died. Method and moats: landscape-mapping.md, moat-analysis.md.
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.
- 1mo ago Changed · -335 lines · -19 tokens per session ba5ef0ca88b3
- 1mo ago Changed 030443b4bf4a
- 2mo ago First seen · 374 lines · 62 tokens per session scan A 704d70c2ac6d
solana-researcher is an agent published in the GitHub repository solanabr/solana-ai-kit (104 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 722 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
solana-researcher compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| solana-researchersolanabr/solana-ai-kit | Agent | 104 | 1mo ago | MIT | A | 43 | Claude Code |
| skill-creatorfusengine/agents | Agent | 34 | 25d ago | MIT | A | 75 | Claude Code |
| code-reviewerfusengine/agents | Agent | 34 | 25d ago | MIT | A | 55 | Claude Code |
| react-expertfusengine/agents | Agent | 34 | 25d ago | MIT | A | 60 | Claude Code |
| security-expertfusengine/agents | Agent | 34 | 25d ago | MIT | A | 48 | Claude Code |
| brainstormingfusengine/agents | Agent | 34 | 25d ago | MIT | A | 42 | Claude Code |
| changelog-watcherfusengine/agents | Agent | 34 | 25d ago | MIT | A | 52 | Claude Code |