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 skills/afx-team/hebb-mind/push-to-githubnpx skills add afx-team/hebb-mind --skill push-to-githubgit clone --depth 1 https://github.com/afx-team/hebb-mindWhat 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 | $0.00054 | $0.01797 |
| Opus 5 | $0.00027 | $0.00898 |
| Sonnet 5 | $0.00011 | $0.00359 |
| Haiku 4.5 | $0.00005 | $0.00180 |
Grade A, and why
push-to-github 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Push to GitHub
Pure "send my committed work upstream" skill. Pushes whatever commits are already in the local branch but not yet on the remote, then opens (or reports) a PR.
Out of scope (handled by /commit):
- Staging files
- Creating commits
- Creating branches
- Anything about uncommitted changes in the working tree
This skill does not look at the working tree at all. Uncommitted files are the user's business; this skill only cares about commits.
Hard rules (MUST)
- MUST NOT run
git add,git commit,git stash, or any staging/committing command. - MUST NOT inspect or report on working-tree cleanliness as a precondition.
- MUST NOT
git push --force,git push --no-verify,git reset --hard,git commit --amend,git config, orgit rebase -i. - MUST abort if there are no unpushed commits on the current branch.
- MUST NOT create a PR when on
main/master(those are the trunk; pushing there is the release trigger —publish.ymlships to PyPI whenpyproject.toml's version changes on main).
Pre-flight (run in parallel)
git rev-parse --git-dir # in a git repo?
git remote get-url origin # has remote?
gh auth status # gh CLI authed?
git rev-parse --abbrev-ref HEAD # current branch
Bail out if any fail:
| Failure | Action |
|---|---|
| Not a git repo | Exit; tell the user |
No origin remote |
Exit; tell user to add one (gh repo create / git remote add origin …) |
gh not authed |
Exit; tell user to run gh auth login themselves (do NOT run it — interactive) |
Detached HEAD (HEAD returned) |
Exit; tell user to checkout a branch |
Workflow
Step 1 — Find unpushed commits
BRANCH=$(git rev-parse --abbrev-ref HEAD)
# Refresh the remote ref so we have an up-to-date view
git fetch origin "$BRANCH" 2>/dev/null || true
# Three cases:
# (a) upstream is set → diff against @{u}
# (b) no upstream but remote branch exists → diff against origin/$BRANCH
# (c) remote branch does not exist → every local commit on this branch is unpushed
if git rev-parse --verify --quiet '@{u}' >/dev/null 2>&1; then
UNPUSHED=$(git log --oneline '@{u}..HEAD')
BASE='@{u}'
elif git ls-remote --exit-code --heads origin "$BRANCH" >/dev/null 2>&1; then
UNPUSHED=$(git log --oneline "origin/${BRANCH}..HEAD")
BASE="origin/${BRANCH}"
else
UNPUSHED=$(git log --oneline HEAD)
BASE='(new branch — no remote counterpart)'
fi
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 · 202 lines · 54 tokens per session scan A 452eda80cb73
push-to-github is a skill published in the GitHub repository afx-team/hebb-mind (50 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 1,797 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
update-changelog
Update docs/CHANGELOG.md from git history, GitHub releases, and code diffs. Use when: writing release notes, syncing the latest changelog entry, summarizing a new tag, or keeping changelog wording concise and consistent.
release
Prepare and publish stable Agent Lightning releases through the repository's version bump, pull-request checks, merge, tag, PyPI trusted-publishing, and versioned-documentation workflows. Use when asked to plan, cut, verify, or explain a release; treat nightly TestPyPI builds as a separate path.
changelog-generation
Changelog generation skill for ZeroClaw releases. Use this skill when the user wants to generate a changelog, prepare release notes, or summarize what changed between versions. Trigger on: 'generate changelog', 'changelog for v0.7.x', 'prepare release notes', 'what changed since ', 'write the changelog'…
herdr-pre-release-audit
Audit herdr release readiness by comparing commits since the base release against next-release changelog and docs. Use when asked to run or apply the repo's pre-release audit, validate docs/next before release, inspect issue refs that release CI will close, or finalize release docs for herdr.
release-notes
Generate user-facing release notes for Intelligent Terminal. Use when asked to write release notes, changelog, what-is-new summary, or prepare a release. Compares git commits between releases, looks up PR-linked issues and community contributors, then outputs formatted notes with "Verbed + Impact + Scenario" style…
release
Cut an AgentOS release via the scripts/publish flow. Use when the user asks to release, publish, cut a release, or bump the AgentOS version.