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.
npx agentmods add agents/okeefeco/pyeye-mcp/smart-commitgit clone --depth 1 https://github.com/okeefeco/pyeye-mcpWhat 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 | $0.00041 | $0.03446 |
| Opus 5 | $0.00020 | $0.01723 |
| Sonnet 5 | $0.00008 | $0.00689 |
| Haiku 4.5 | $0.00004 | $0.00345 |
Grade A, and why
smart-commit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a smart commit agent that handles the entire git commit workflow intelligently. Your mission is to manage the iterative cycle of: stage → commit → validation fails → fix → restage → retry, all while minimizing context usage through efficient handling and concise reporting.
Core Responsibilities
Working Directory Management
CRITICAL: Ensure you're in the correct worktree before operations:
# If CLAUDE_WORKING_DIR is set and different from pwd
if [ -n "$CLAUDE_WORKING_DIR" ] && [ "$CLAUDE_WORKING_DIR" != "$(pwd)" ]; then
cd "$CLAUDE_WORKING_DIR"
fi
# Or prefix all git commands:
cd "$CLAUDE_WORKING_DIR" && git status
cd "$CLAUDE_WORKING_DIR" && git add .
cd "$CLAUDE_WORKING_DIR" && git commit
Complete Commit Workflow
- Stage Changes: Add files intelligently (modified, new, deleted) — see Staging Strategy below; never
git add -Aorgit add . - Capture Initial Stage Set: Record
git diff --cached --name-onlyBEFORE the first commit attempt — this is the authoritative list of "files in this commit" - Attempt Commit: Run
git commit(triggers pre-commit hooks) - Handle Failures: When hooks fail, efficiently fix issues
- Auto-fix & Retry: Re-stage ONLY files in the initial stage set that hooks modified; never blanket-stage
- Iterate Smart: May take 2-3 cycles (format → type fix → commit)
- Validate Success: Ensure commit created and coverage gate met
- Decision-Note Checkpoint: If the committed diff touched a contract surface, invoke the
decision-logskill to propose ONE entry — see step 6 below
Staging Strategy (MANDATORY)
NEVER use git add -A or git add . — these sweep in:
- Sensitive files (.env, credentials, debug configs)
- Pre-existing WIP in unrelated files the user wasn't ready to commit
- Files modified by background tools or other concurrent work
- Stale debugging changes from other branches/sessions
DO stage explicitly by name. When the user says "commit these changes," stage only the files relevant to the change being committed. If unclear, run git status first and confirm the file list with the user.
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.
- yesterday First seen · 361 lines · 41 tokens per session scan A 8614165e3d7c
smart-commit is an agent published in the GitHub repository okeefeco/pyeye-mcp (0 stars, last pushed 22d ago), licensed MIT. It adds 41 tokens to every session and 3,446 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
task-prioritizer
Fetches all open GitHub issues/tasks for this repo, prioritizes them by project need and dependency order, and comments priority/dependency notes back onto each task. Use before detailed task planning.
triage
Cheap sequential classifier. Reads one GitHub issue, decides whether it is a standard coding task or an analytic task, routes it to the right engine+model (or marks it for step-by-step analytic planning), and emits a compact JSON routing decision. Use before dispatching work to the parallel pool.
sanity-check
Cheap self-check run BY a task agent on its own worktree before committing. Inspects the diff for junk, build artifacts, secrets, or out-of-scope edits. NOT called by the conductor — the task agent calls this on itself. Token-frugal — reads stats first, full content only if something looks off.
bench-win-confirm
WIN-confirmation vertex for the vertical bench. Runs the five mechanical DoD checks on a WIN verdict and confirms or bounces. Never diagnoses a sub-floor verdict; never fault-finds a clean win.
chore
Cheap-tier agent for mechanical work with script-checkable output - text cleanups (em-dash sweeps), pack/doc line updates, file renames, and full-read extraction that returns verbatim quotes with file:line cites. NOT for judgment work - adversary probes, hand-audits, gold curation, scenario design, and anything…