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/build-program)<a href="https://agentmods.dev/commands/solanabr/solana-ai-kit/build-program"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/build-program/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/build-program"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/build-program.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 | $0.00561 |
| Opus 5.5 | $0.00007 | $0.00224 |
| Sonnet 5.5 | $0.00004 | $0.00112 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
build-program scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
2 near-identical copies found in the catalogue:
- build-program — 100% identical, 195 lines differ
- build-program — 100% identical, 195 lines differ
How it starts
The opening of the file, as written. The whole thing — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build the program(s) in this workspace ($ARGUMENTS: optional program name) so target/deploy/*.so, and for Anchor target/idl/*.json, are ready for tests and deploys. Toolchain errors not covered below: common-errors.md.
Steps
- Build:
- Anchor:
anchor build(-p <name>for one program). For a new, never-deployed program, runanchor keys syncafter the first build and rebuild, sodeclare_id!andAnchor.tomlmatchtarget/deploy/<name>-keypair.json. Skip it for a deployed program whose keypair is not intarget/deploy/: it would rewritedeclare_id!to a fresh address. - Pinocchio or native:
cargo build-sbf. - Anything headed to mainnet:
anchor build --verifiable. It needs Docker, writestarget/verifiable/<name>.so, and is deployed withanchor deploy --verifiable. Non-Anchor programs usesolana-verify build.
- Anchor:
- Check the output: each
.soand its size (deploy rent scales with it:solana rent <bytes>), the IDL for Anchor programs, and the program IDs (solana address -k target/deploy/<name>-keypair.json). cargo fmt --checkandcargo clippy --all-targets -- -D warnings.
Failure fixes
- Platform-tools corrupted or half-downloaded:
cargo build-sbf --force-tools-install. feature edition2024 is requiredor "requires rustc 1.xx":cargo build-sbfuses the Rust/Cargo bundled in platform-tools, not your rustup toolchain. Pin the offending crate (cargo update -p <crate> --precise <older version>) or move to newer platform-tools (agave-install update, or--tools-version).overflow-checks must be specified: setoverflow-checks = trueunder[profile.release]in the workspaceCargo.toml. It also makes unchecked arithmetic panic instead of silently wrapping.- Binary too large:
lto = "fat"andcodegen-units = 1in[profile.release];opt-level = "s"or"z"trades CU for size; drop heavy dependencies.
Output
Programs built, .so sizes, program IDs, IDL status, fmt and clippy results.
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 · -163 lines · +9 tokens per session 9b46b0ef1fef
- 26d ago Changed ca1eb9d7c322
- 1mo ago First seen · 189 lines · 9 tokens per session scan A 5c2d2bcdd5a7
build-program 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 561 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
cargo-metadata
Command "cargo-metadata" from olorehq/olore, covering cargo-metadata(1), name, synopsis, description and output format.
cargo-report
Command "cargo-report" from olorehq/olore, covering cargo-report(1), name, synopsis, description and options.
cli-review
Review Rust CLI applications for UX, error handling, testing, and cross-platform compatibility.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.