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/commands/solanabr/solana-ai-kit/plan-feature)<a href="https://agentmods.dev/commands/solanabr/solana-ai-kit/plan-feature"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/plan-feature/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/commands/solanabr/solana-ai-kit/plan-feature"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/plan-feature.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 | $0.00018 | $0.00538 |
| Opus 5.5 | $0.00007 | $0.00215 |
| Sonnet 5.5 | $0.00004 | $0.00108 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
plan-feature 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 25d 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:
- plan-feature — 100% identical, 356 lines differ
- plan-feature — 100% identical, 356 lines differ
How it starts
The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write an implementation plan for the feature described in $ARGUMENTS. Plan only; write no code. If .claude/context/idea.md exists (written by the idea-sprint skill), start from it instead of re-asking what it already answers.
Steps
- Read the code the feature touches. Ask the user only about decisions that change the design: who signs and who pays rent, expected scale and contention, upgradeability, target clusters, Token vs Token-2022.
- If the account model or the program split is still open, spawn
solana-architectand plan from its design. - Write the plan below. Size each account from its fields (Anchor 1.x:
T::DISCRIMINATOR.len() + T::INIT_SPACE), price its rent, and give each instruction a CU estimate that/profile-cuwill verify later.
Plan format
- Summary: the problem, who it is for, and the one flow that must work.
- Accounts: per account: purpose, PDA seeds, fields with sizes, total bytes and rent, and which instructions create, mutate and close it.
- Instructions: per instruction: accounts (signer, writable, PDA), arguments with bounds, checks, state changes, events, errors, CU estimate.
- Integrations: CPIs into other programs, SDKs, RPC and indexer needs.
- Clients: generated client (
/generate-idl-client), frontend, Unity or backend touchpoints. - Phases: ordered; each lists the files to add or change, the tests that prove it done, and its review gate (
/test-rust,/diff-review, plus/audit-solanafor code that holds funds). - Risks: CU and transaction size (1232 bytes for legacy and v0, 4096 for v1), account growth and realloc, write-lock contention on shared accounts, upgrades and data migration, changes in external programs.
- Tests: happy paths, every error path, adversarial cases (wrong signer, substituted or duplicated accounts, boundary amounts), and Surfpool mainnet-fork tests for CPIs into live programs.
- Rollout: devnet first through
/deploy, then the mainnet and upgrade-authority plan.
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.
- 25d ago Changed · -320 lines · +8 tokens per session de8c3f9a1193
- 1mo ago First seen · 348 lines · 10 tokens per session scan A c9f93026166b
plan-feature is a command published in the GitHub repository solanabr/solana-ai-kit (104 stars, last pushed 26d ago), licensed MIT. It adds 18 tokens to every session and 538 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 commands, from other repositories
apex
APEX Methodology - The systematic Analyze-Plan-Execute-eLicit-eXamine approach for intelligent development. Reduces hallucination and defect risk through mandatory parallel research, self-review, and validation gates.
explain-architecture
Analyze and explain software architecture with ASCII diagrams and pattern detection. Creates visual representations of system design.
prompt
Create or optimize prompts using best practices.
design-audit
Audit an existing HTML/CSS design. Deterministic checks only (contrast, fonts, colors, states, dark mode) plus a visual pass. No generation.
amend
Amend last commit safely. Use for amend, fix last commit, update commit, modify commit.
test
Test commit. Use for add tests, update tests, test coverage, unit test, spec.