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 commands/cafitac/hermit-agent/code-push-hermitgit clone --depth 1 https://github.com/cafitac/hermit-agentWhat 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 | $0.00000 | $0.01309 |
| Opus 5 | $0.00000 | $0.00655 |
| Sonnet 5 | $0.00000 | $0.00262 |
| Haiku 4.5 | $0.00000 | $0.00131 |
Grade A, and why
code-push-hermit 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 2d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/code-push-hermit — Claude writes the PR prose, Hermit does the git work
Commit-and-push are the textbook grunt-work target: short, mechanical,
deterministic, and unrelated to reasoning. This skill keeps the
deciding parts in Claude and delegates the git commands to Hermit.
Arguments
$ARGUMENTS — PR number (required for the PR description update step;
the commit+push works without it).
--model <model_name>— executor model override.
Prerequisites
- Clean or stageable working tree with actual changes.
- Hermit gateway + MCP server running.
ghCLI authenticated if you want the PR-description step.
Workflow
Step 1 — pre-flight (Claude)
git status --porcelainin the worktree — confirm changes exist.- Refuse if the branch is
mainordevelop. - Scan staged and unstaged files for sensitive names (
.env,*.pem,*.key,credentials*). If any are present, report and stop — ask the user whether to add them to.gitignore. - Read the last few commits to learn the project's message style (length, prefix conventions, language).
Step 2 — lock
mkdir -p .hermit
cat > .hermit/active-task.lock <<EOF
{
"task_id": "<filled-after-run_task>",
"started_at": "$(date -Iseconds)",
"skill": "code-push-hermit",
"pr": "$ARGUMENTS",
"cwd": "<worktree_path>"
}
EOF
Step 3 — delegate commit + push to Hermit
mcp__hermit__run_task(cwd=<worktree>, background=true, model=<--model or "">)
You are Hermit. Commit and push the pending changes in this worktree
for PR #<PR-number>.
Context:
- Branch: <branch>
- PR title: <title>
- Changed files (already reviewed by Claude and confirmed in scope):
<file list>
Rules:
1. Safety:
- Refuse if the branch is main or develop.
- Never stage .env, *.pem, *.key, credentials*.
- Use `git -C <worktree> ...` (no `cd && git ...`).
2. Match the project's commit-message style — read
`git log --oneline -5`. Prefix convention, length, language.
3. Split the changes into logical commits if they span multiple
concerns (e.g. refactor + feat).
4. Per commit:
- `git add` only the relevant files (never `-A` / `.`).
- One conventional-prefix message (fix/feat/refactor/chore/test).
- Do NOT add Co-Authored-By or AI attribution lines.
5. Push: `git push`, or `git push -u origin <branch>` if the branch
has no upstream yet.
Return: commit list (short hash + message), push result, anything
skipped with a reason.
Do NOT:
- Edit the PR description — Claude does that.
- Create commits for files outside the current PR diff.
- Update external ticket systems.
Obey HERMIT.md, .hermit/rules/, and .claude/rules/.
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.
- 2d ago First seen · 155 lines · 0 tokens per session scan A 4104be120758
code-push-hermit is a command published in the GitHub repository cafitac/hermit-agent (4 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,309 tokens. 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 commands, from other repositories
toefl-grade
TOEFL 답안/녹음 채점 — 로컬 LLM(Ollama)과 whisper.cpp로 4개 영역을 채점하여 SCORES.md에 점수를 누적 기록한다.
toefl-practice
TOEFL 유형 문제 생성 — 로컬 LLM(Ollama)이 reading/listening/speaking/writing 영역의 실전형 문제를 생성하여 practice/에 저장한다.
toefl-drill
취약 영역 집중 반복 — SCORES.md에서 약점을 식별하여 해당 유형의 문제를 연속 생성/채점하는 딥 드릴 루프를 안내한다.
toefl-roadmap
이번 주 토플 학습 로드맵/과제 표시 — schedule.yaml에서 사용자가 지정한 학습 기간·요일·시간대·주차별 목표를 읽어 현재 날짜 기준으로 안내한다.
toefl-status
토플 학습 현황 요약 — schedule.yaml(D-day/목표점수) + JOURNAL.md/SCORES.md를 파싱하여 진행률, 영역별 점수 추이, 목표 대비 갭, 시험일까지 남은 일수를 표시한다.
opencode
Manage OpenCode/Zen connections, switch models, and configure local Ollama.