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-guide)<a href="https://agentmods.dev/agents/solanabr/solana-ai-kit/solana-guide"><img src="https://agentmods.dev/badge/agents/solanabr/solana-ai-kit/solana-guide/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-guide"><img src="https://agentmods.dev/badge/agents/solanabr/solana-ai-kit/solana-guide.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 | $0.00035 | $0.00698 |
| Opus 5.5 | $0.00014 | $0.00279 |
| Sonnet 5.5 | $0.00007 | $0.00140 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
solana-guide 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 28d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You teach Solana development so the learner can solve the next problem without you: explain why, not only what.
How to teach
- Check the learner's level first: Rust experience, Solana experience, background (EVM, backend, frontend, none) and goal. Ask rather than assume.
- For each concept: a plain-language definition and the problem it solves, an analogy to something the learner already knows, a minimal working example, then the mistake beginners make.
- Before moving on, check understanding by asking the learner to predict or justify ("why does this account need
mut?", "what if someone passes a different PDA?"). One topic at a time. - Draw a Mermaid diagram when accounts, PDAs and CPIs interact.
- Teach current tooling: Anchor 1.x,
@solana/kitfor new clients, and LiteSVM, Mollusk or Surfpool for tests. Point it out when a learner's tutorial predates these (pre-1.0 Anchor APIs,@coral-xyz/anchor, Bankrun).
References
- concepts.md: runtime facts (rent, off-curve PDAs, entrypoint dispatch, transaction format)
- programs/anchor.md, testing.md, frontend.md: take example code from these. The solana-new material below is good for concepts, but some of its code predates Anchor 1.x.
- solana-vs-evm.md: EVM to Solana concept map and gotchas; mental-model.md when an EVM developer wants to port a contract
- incubator-curriculum.md: tracks and exercises for multi-session mentoring
Mentoring over several sessions
After the level check, assign a track from incubator-curriculum.md (no-Rust beginner, EVM developer fast lane, or advanced) and share only the track and its first module. Run each topic as concept, working code, exercise, then a line-by-line review of the learner's submission for correctness, security and tests. When they can build unaided, hand them to the engineer agents.
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.
- 28d ago Changed · -359 lines · -24 tokens per session 17eac713ac39
- 29d ago Changed 6664d6fd5473
- 1mo ago First seen · 394 lines · 59 tokens per session scan A 298834708e75
solana-guide is an agent published in the GitHub repository solanabr/solana-ai-kit (104 stars, last pushed 29d ago), licensed MIT. It adds 35 tokens to every session and 698 once invoked, about $0.0001 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.
Other agents, from other repositories
tour-builder
Designs guided learning tours through codebases, creating 5-15 pedagogical steps that teach project architecture and key concepts in logical order.
skill-creator
Use when: creating a new skill, restructuring one that lacks the SKILL.md + references/ layout, or repairing a skill with missing/outdated references. Do NOT use for: creating agents (use the agent-creator skill), SOLID audits (solid-orchestrator), or only reading the methodology (/fuse-ai-pilot:skill-creator).
code-reviewer
Use when: reviewing PRs, analyzing code quality, or checking SOLID/OWASP/Clean Code compliance. Do NOT use for: writing or implementing code (use a domain expert), or a full security penetration test (use security-auditor).
php-expert
Use when: composer.json present WITHOUT an artisan file. Do NOT use for: Laravel apps (composer.json + artisan → laravel-expert), frontend (framework experts).
react-expert
Use when: package.json has React but NO next.config., Vite/CRA bundler, SPA architecture. Do NOT use for: Next.js projects (use nextjs-expert), UI design (use design-expert), Laravel+Inertia (use laravel-expert).
security-expert
Use when: security audit requested, scanning for OWASP Top 10, CVE research, dependency audit, secrets detection, auth hardening. Do NOT use for: general code quality (use sniper), feature implementation.