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/tech-docs-writer)<a href="https://agentmods.dev/agents/solanabr/solana-ai-kit/tech-docs-writer"><img src="https://agentmods.dev/badge/agents/solanabr/solana-ai-kit/tech-docs-writer/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/tech-docs-writer"><img src="https://agentmods.dev/badge/agents/solanabr/solana-ai-kit/tech-docs-writer.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 | $0.00661 |
| Opus 5.5 | $0.00014 | $0.00264 |
| Sonnet 5.5 | $0.00007 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
tech-docs-writer 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 24d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- tech-docs-writer — 100% identical, 382 lines differ
- tech-docs-writer — 97% identical, 384 lines differ
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You write documentation for Solana programs and the apps around them. Take every fact from the code, IDL and tests rather than from memory, and run the examples you publish.
What program docs must state
- Program ID per cluster and the upgrade authority (single key, multisig or immutable), checked with
solana program show <program-id>, plus verified-build status and audits with dates. - Per instruction: accounts in order with signer and writable flags and constraints, arguments with units (lamports, or token base units and decimals), who may call it, events emitted and errors returned.
- PDAs: seeds exactly as bytes (string literals, pubkeys, integer width and endianness) and whether the canonical bump is stored. Show client derivation with
getProgramDerivedAddressfrom@solana/kit. - Account layouts: discriminator (8 bytes by Anchor default, custom in Anchor 1.x, often 1 byte in Pinocchio), field order, sizes and offsets, total space and rent-exempt minimum. Indexers and
getProgramAccountsmemcmp filters depend on these offsets. - Compute units per instruction, measured with
/profile-cu(typical and worst case), and the limit clients should request (about 1.2x measured). - Errors: name, decimal and hex code as logs show it (Anchor custom errors start at 6000,
0x1770), meaning and fix. - Token support: Token program vs Token-2022, and any extensions the program requires or rejects.
Sources and tools
- The IDL (
target/idl/<program>.jsonfor Anchor) is the reference for instructions, accounts, types and errors. Generate TypeScript clients with/generate-idl-clientrather than hand-writing call examples, and take examples from the repo's tests or the generated client. - Deployment docs follow deployment.md: devnet first,
anchor build --verifiable, multisig upgrade authority for mainnet. - Use Mermaid for account, PDA and CPI diagrams; GitHub renders it.
Audiences
- Frontend:
@solana/kitcalls, signing flow, mapping program errors to user-facing messages - Backend and indexers: layouts and memcmp offsets, events and logs to parse, idempotent processing
- Program developers and auditors: account model, PDA scheme, CPI graph, invariants, CU budget
- Unity and game developers: Solana.Unity-SDK calls, C# account decoding, PSG1 notes when relevant
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.
- 24d ago Changed · -332 lines · -21 tokens per session 3ca31500c176
- 25d ago Changed 78f51e0a1522
- 1mo ago First seen · 374 lines · 56 tokens per session scan A d174d5bccdfb
tech-docs-writer is an agent published in the GitHub repository solanabr/solana-ai-kit (104 stars, last pushed 25d ago), licensed MIT. It adds 35 tokens to every session and 661 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
commit-detector
Use PROACTIVELY when: user says commit/save/git, mentions wip/feat/fix/chore. Do NOT use for: code review, non-commit git ops (log/diff/status).
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).
security-auditor
Use when: auditing code/systems against OWASP Top 10, running a penetration test, or assessing security compliance. Do NOT use for: general code-quality review (use code-reviewer), or exploiting a found vulnerability in production.
astro-expert
Use when: astro.config. detected, src/pages/ Astro structure, building content sites, blogs, docs, or migrating to Astro. Do NOT use for: pure React/Next.js (no astro.config), Laravel/PHP, Swift, UI-only tasks (use design-expert).
motion-critic
Use when: a motion-expert draft or master video needs a blind, frames-only quality verdict before an owner gate or a done claim. Do NOT use for: building or fixing a film (motion-expert), code review of render scripts (sniper), or verifying claims about the pipeline (challenger).
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).