write-docs

A documentation command for Solana programs, APIs, and software components. Solana is a blockchain platform, and a program is its name for code that runs on the network.

In plain words
What is it for?
Use it to document Solana instructions, accounts, addresses, errors, compute use, SDKs, APIs, components, and README files.
Why use it?
It turns technical code details into reference material that explains setup, behavior, inputs, errors, security, and examples.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/solanabr/solana-ai-kit/write-docs
Clone the repo
git clone --depth 1 https://github.com/solanabr/solana-ai-kit

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 500 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.00500
Opus 5 $0.00005 $0.00250
Sonnet 5 $0.00002 $0.00100
Haiku 4.5 $0.00001 $0.00050

Measured 2d ago against content hash ca338813e5af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write-docs 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 2d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.claude/commands/write-docs.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate comprehensive documentation for Solana blockchain code.

Code to Document

$ARGUMENTS

Documentation Strategy

1. Identify Documentation Type

Type What to Generate
Program Instructions, accounts, PDAs, errors, security, CU
SDK/API Functions, params, returns, errors, examples
Component Props/properties, events, usage patterns
README Overview, setup, quick start, deployment

2. Documentation Requirements

For Instructions/Endpoints:

  • Accounts table (name, type, description)
  • Arguments table (name, type, validation)
  • Error codes with descriptions
  • Access control notes
  • Compute units estimate
  • Working code example

For Account Structures:

  • Purpose and lifecycle
  • Size calculation (include discriminator)
  • Field table with types and offsets
  • PDA seeds (if applicable)
  • Rent cost

For README:

  • Program IDs (mainnet/devnet)
  • Installation command
  • Quick start example
  • Instruction summary table
  • Security/audit status

3. Best Practices

Do:

  • Document ALL public functions/instructions
  • Include working code examples
  • Explain "why", not just "what"
  • Include error scenarios
  • Update docs when code changes

Don't:

  • Document obvious code
  • Leave non-compiling examples
  • Skip security considerations
  • Forget to document errors

Output

Generate documentation appropriate to the code type:

  1. Programs: Instruction docs, account docs, error codes
  2. SDKs: Function docs, type definitions, examples
  3. Components: Props, events, usage patterns
  4. Projects: README with setup and deployment

For complex projects, delegate to tech-docs-writer agent.

Read the full file on GitHub · 77 lines

Changes

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.

  1. 2d ago First seen · 77 lines · 11 tokens per session scan A ca338813e5af

Subscribe to this mod's changes

write-docs is a command published in the GitHub repository solanabr/solana-ai-kit (98 stars, last pushed 12d ago), licensed MIT. It adds 11 tokens to every session and 500 once invoked, about $0.0001 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 2026-08-30.