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/quick-commit)<a href="https://agentmods.dev/commands/solanabr/solana-ai-kit/quick-commit"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/quick-commit/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/quick-commit"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/quick-commit.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 | $0.00015 | $0.00585 |
| Opus 5.5 | $0.00006 | $0.00234 |
| Sonnet 5.5 | $0.00003 | $0.00117 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
quick-commit 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 22d 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:
- quick-commit — 100% identical, 529 lines differ
- quick-commit — 100% identical, 529 lines differ
How it starts
The opening of the file, as written. The whole thing — 19 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit the current work with a conventional commit message. $ARGUMENTS, if given, is the message or a hint for it.
Steps
- Branch. On
mainormaster, propose<type>/<scope>-<description>-<DD-MM-YYYY>(e.g.feat/program-vault-15-01-2026; date fromdate +%d-%m-%Y; type from the change: feat, fix, docs, test, refactor, chore) and ask: create it, use a custom name, or stay. Create it withgit checkout -b <name>; uncommitted changes come along. - Stage. If
git status --shortis empty, stop. If something is already staged, commit only that. Otherwise stage modified and new files, leaving out secrets and build output (.env,.env.local,*keypair*.json,id.json,target/,node_modules/) and saying what was left out. - Format, then re-stage what it touched (
git add -u):cargo fmtfor Rust,npx prettier --writeon the changed TS/JS/JSON files,ruff formatfor Python. - Lint:
cargo clippy --all-targets -- -D warnings;npm run lintwhenpackage.jsondefines it. Fix what is quick and report the rest. - Message:
type(scope): summary, imperative, under 72 characters, written fromgit diff --cachedrather than from file names. Types: feat, fix, refactor, perf, test, docs, style, chore, ci. Scope is the area touched (program, frontend, tests, docs, deps). Add a body with the why when the change is not obvious. No AI attribution orCo-Authored-Bytrailer (the kit setsattributionto empty strings in settings.json). - Commit. Show
git diff --cached --statand the message, thengit commit. The kit's PreToolUse hook ongit commitre-runscargo fmt --check, clippy andcargo test --libfor program crates, and prettier plustsc --noEmitfor JS/TS projects. It blocks the commit on a failure, or after it reformats files. Fix, re-stage and retry; don't skip hooks with--no-verify.
Output
Branch, commit hash and message, files committed, and any lint warnings left unfixed. This only runs quick checks; run the full suites (/test-rust, /test-ts) before pushing.
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.
- 22d ago Changed · -507 lines · +2 tokens per session f0b8e24e458e
- 1mo ago First seen · 526 lines · 13 tokens per session scan A 383de92f33c7
quick-commit is a command published in the GitHub repository solanabr/solana-ai-kit (104 stars, last pushed 22d ago), licensed MIT. It adds 15 tokens to every session and 585 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
commit
Smart conventional commit with security validation, branch flow enforcement, and auto-detection. Use for git commit, commit changes, save work, stage and commit.
run-tasks
Execute GitHub issues using full EPCT workflow (Explore-Plan-Code-Test). Converts issue requirements into completed PR.
amend
Amend last commit safely. Use for amend, fix last commit, update commit, modify commit.
chore
Chore commit. Use for maintenance, deps, dependencies, config, cleanup, housekeeping.
docs
Documentation commit. Use for update docs, documentation, readme, jsdoc, comments.
feat
Quick feature commit. Use for new feature, add feature, implement, create new.