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/fmarzochi/egc/prp-commitgit clone --depth 1 https://github.com/Fmarzochi/EGCWrote 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/fmarzochi/egc/prp-commit)<a href="https://agentmods.dev/commands/fmarzochi/egc/prp-commit"><img src="https://agentmods.dev/badge/commands/fmarzochi/egc/prp-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 | $0.00015 | $0.00524 |
| Opus 5 | $0.00008 | $0.00262 |
| Sonnet 5 | $0.00003 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
prp-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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smart Commit
Input: $ARGUMENTS
Turn "commit the parser fix" into the right git add set and a clean conventional commit, without the user naming a single path.
Step 1: Inventory
git status --porcelain
git diff --stat
If there is nothing to commit, say so and stop.
Step 2: Resolve the target
$ARGUMENTS |
Selection |
|---|---|
| Blank | All modified and untracked files |
| Plain-English description | Files whose path, directory, or diff content match the description |
Matching is semantic, not string-based: "the parser fix" selects the files whose diff touches parsing logic, even if no path contains the word "parser". When the description matches nothing, show the changed files and ask; never guess into an empty commit.
Step 3: Split into atomic commits
One commit = one concern. If the selected files mix concerns (a bug fix plus an unrelated rename), propose a split and create the commits in sequence. Never bundle unrelated changes to save a step.
Step 4: Guard
Before staging, scan the selected diff for:
- Secrets: keys, tokens, passwords,
.envcontent. Finding one aborts the commit for that file with a warning. - Debug leftovers:
console.log, commented-out blocks, stray TODO added by this change. Flag them; commit only if the user confirms. - Files that are clearly accidental: lockfile churn without dependency changes, editor artifacts.
Step 5: Commit
Write a conventional commit message derived from the diff, not from the user's phrasing:
{type}({scope}): {what changed, imperative, under 72 chars}
{body only when the diff does not speak for itself: the why, not the what}
Types: feat, fix, docs, refactor, test, chore, ci, perf.
Sign-off: run git commit -s when the repository enforces DCO (a DCO check in CI or a CONTRIBUTING requirement); plain git commit otherwise.
Output
{n} commit(s) created:
{short-hash} {message}
Not committed: {files left out and why, or "nothing"}
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 · 63 lines · 15 tokens per session scan A f64ce66e9424
prp-commit is a command published in the GitHub repository Fmarzochi/EGC (48 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 524 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
build
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.
commit
Auto-stage, review, and commit all changes with a conventional commit message.
commit
Create a conventional commit/s from current changes.
commit
Create one conventional commit from an already-scoped change; never push.
pr-package
Prepare a clean delivery package for GitHub from the real git diff vs an explicit base branch, persisted as PRPACKAGE.md (or PRPACKAGE. .md for multi-repo tasks). Produces branch name, commit messages, fetch, checkout, add, commit, and push commands, PR title and body, and reviewer attention points; never invents work…
commit
Commit on a new branch with conventional message.