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/commit-claude-config)<a href="https://agentmods.dev/commands/solanabr/solana-ai-kit/commit-claude-config"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/commit-claude-config/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/commit-claude-config"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/commit-claude-config.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 | $0.00025 | $0.00634 |
| Opus 5.5 | $0.00010 | $0.00254 |
| Sonnet 5.5 | $0.00005 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
commit-claude-config 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 23d 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.
How it starts
The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
install.sh gitignores the kit config by default, in a marked .gitignore block covering .claude/ (or .agents/), CLAUDE.md, .mcp.json and .gitmodules. This command opts the project in, so the config travels with the repo. The ext/ skill submodules stay ignored: they are upstream content, and tracking .gitmodules is enough for a --recurse-submodules clone to repopulate them.
Steps
- Preflight. Stop unless inside a git work tree, and tell the user to run
git initfirst.CONFIG_DIRis.claudeif it exists, else.agents(--agentsinstalls); with neither there is nothing to commit. - Un-ignore. Remove the marked block and leave the
ext/and local-only sections alone. Writing through a temp file keeps it portable across GNU and BSD sed. If the block is already gone, continue.if [ -f .gitignore ] && grep -qF ">>> solana-ai-kit config" .gitignore; then sed '/# >>> solana-ai-kit config/,/# <<< solana-ai-kit config <<</d' .gitignore > .gitignore.tmp \ && mv .gitignore.tmp .gitignore fi - Stage. Since
ext/is still ignored, this records agents, commands, skills and settings but not the submodule trees.git add .gitignore 2>/dev/null || true for p in .gitmodules CLAUDE.md .mcp.json "$CONFIG_DIR"; do [ -e "$p" ] && git add "$p"; done git diff --cached --name-status - Confirm. If nothing is staged (
git diff --cached --quiet), report that the config is already tracked and stop. Otherwise show the staged list and wait for the user's go-ahead. - Commit:
git commit -m "chore: track Solana AI Kit config". The kit's commit hook and any.git/hooks/pre-commitrun as usual.
Notes
- To go back to ignoring the config, re-run
install.sh(it re-adds the block only if absent), or rungit rm --cached -r .claude CLAUDE.md .mcp.json .gitmodulesand restore the.gitignorelines. - To version the
ext/submodules as well (rarely needed; they are large upstream trees), remove the$CONFIG_DIR/skills/ext/line from.gitignoreand rungit submodule update --initso real gitlinks exist beforegit add.
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.
- 23d ago Changed · -42 lines · -10 tokens per session d1a7ba48f60e
- 24d ago Changed · +1 lines 7fc5a20f32c7
- 1mo ago First seen · 73 lines · 35 tokens per session scan A 8e7287ef4364
commit-claude-config is a command published in the GitHub repository solanabr/solana-ai-kit (104 stars, last pushed 24d ago), licensed MIT. It adds 25 tokens to every session and 634 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.
docs
Documentation commit. Use for update docs, documentation, readme, jsdoc, comments.
feat
Quick feature commit. Use for new feature, add feature, implement, create new.
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.