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/jonathan-vella/apex-acceleratorWrote 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/jonathan-vella/apex-accelerator/apex-git-commit)<a href="https://agentmods.dev/commands/jonathan-vella/apex-accelerator/apex-git-commit"><img src="https://agentmods.dev/badge/commands/jonathan-vella/apex-accelerator/apex-git-commit.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.01765 |
| Opus 5 | $0.00026 | $0.00882 |
| Sonnet 5 | $0.00010 | $0.00353 |
| Haiku 4.5 | $0.00005 | $0.00177 |
Grade A, and why
apex-git-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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit, Push & PR (CLI-only)
Stage all changes except anything under agent-output/, infra/, or
.github/skills/sensei/ (the sensei exclusion is lifted only when the
current branch is feat/skills-sensei), auto-generate a conventional
commit, push to the current branch, then ask whether to open a new PR or
update an existing one. Uses git and gh only — no MCP tools.
Scope
- Workspace must be a git repository with
originconfigured. ghCLI must be authenticated (GH_TOKENis set in the devcontainer).- Excluded paths (always):
agent-output/,infra/. - Excluded path (conditional):
.github/skills/sensei/— included only whengit branch --show-currentreturnsfeat/skills-sensei. - Never commit to
main. Never force-push.
Inputs
| Variable | Source | Default |
|---|---|---|
| subject | argument-hint or generated from diff | auto |
| branch | git branch --show-current |
current branch |
| sensei | derived: branch == feat/skills-sensei |
exclude sensei |
| pr_mode | user choice (new / update / skip) | ask |
| pr_base | user choice | main |
Workflow
Step 0 — Compute the exclusion pathspec
Resolve the active branch and build the pathspec used by every subsequent
git command:
BRANCH="$(git branch --show-current)"
if [[ "$BRANCH" == "feat/skills-sensei" ]]; then
EXCLUDES=(':!agent-output' ':!infra')
else
EXCLUDES=(':!agent-output' ':!infra' ':!.github/skills/sensei')
fi
Every git add/git status/git diff command below uses
-- . "${EXCLUDES[@]}" to apply the exclusion list consistently. If the
user is on feat/skills-sensei the sensei skill files are eligible for
staging; on every other branch they are skipped.
Step 1 — Inspect
Run these in parallel and show the output:
echo "$BRANCH"
git status --short -- . "${EXCLUDES[@]}"
git diff --stat HEAD -- . "${EXCLUDES[@]}"
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 · 207 lines · 52 tokens per session scan A f59f4ab7a373
apex-git-commit is a command published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,765 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 2026-09-07.
Other commands, from other repositories
prune-source
Guided removal of a source store from sources/supported-stores.json — coherence check first, comment-out for one cycle, then delete.
commit
Use the text the user typed after the command name as the request for this command.
cm
Stage working tree changes and create a Conventional Commit (no push).
cp
Stage, commit, and push the current branch following git governance rules.
explain
/explain Explain the last agent action (quick mode) /explain --verbose Full trace with file changes and decision rationale /explain --story STORY-XXX All actions for a story in chronological order /explain --agent Last action by a specific agent /explain --session All actions from a specific session /explain --diff…
git-commit
Create a git commit for the current changes using Conventional Commits-style format.