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/devoxx/devoxxgenieideaplugin/git-commit-push-prnpx skills add devoxx/DevoxxGenieIDEAPlugin --skill git-commit-push-prgit clone --depth 1 https://github.com/devoxx/DevoxxGenieIDEAPluginWhat 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 | $0.00053 | $0.00696 |
| Opus 5 | $0.00026 | $0.00348 |
| Sonnet 5 | $0.00011 | $0.00139 |
| Haiku 4.5 | $0.00005 | $0.00070 |
Grade A, and why
git-commit-push-pr 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit, Push & PR
Context
- Current git status: !
git status - Current git diff (staged and unstaged changes): !
git diff HEAD - Current branch: !
git branch --show-current - Main branch: !
git rev-parse --verify main 2>/dev/null && echo main || echo master - Recent commits: !
git log --oneline -10
Your task
Review the changes in the repo and ship them as a pull request in one go.
Step 1 — Analyze changes and plan commits
Before committing, analyze git status and git diff HEAD to identify logically distinct groups of changes. Group by feature or concern — for example:
- New files that form a self-contained module → one commit
- Modifications to an existing file that depend on the new module → separate commit
- Config or tooling changes → separate commit
Print a short commit plan (list of planned commits with the files in each) so the grouping is visible.
Step 2 — Commit
- Create one commit per logical group identified above. Stage only the files for that group using explicit file names (never
git add -A; never stage.envor credential files). - Write a clean, descriptive commit message for each commit using conventional commits style.
- End every commit message with:
Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]> - Use a HEREDOC to pass the commit message for correct formatting.
Step 3 — Push
- If the current branch is
mainormaster, create a new feature branch first (use a descriptive name based on the changes). - Push the branch to origin with
-uto set upstream tracking.
Step 4 — Pull Request
- Create a PR using
gh pr createtargeting the main branch. - Keep the PR title short (under 70 characters), using conventional commit style.
- Use a HEREDOC for the PR body with this format:
## Summary
<1-3 bullet points describing the changes>
## Test plan
- [ ] <testing checklist items>
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Step 5 — Report
- Print the PR URL so the user can see it.
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 · 71 lines · 53 tokens per session scan A 1efae5b8b38f
git-commit-push-pr is a skill published in the GitHub repository devoxx/DevoxxGenieIDEAPlugin (677 stars, last pushed 5d ago), licensed MIT. It adds 53 tokens to every session and 696 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
carta-compensation-benchmarks
Retrieves Carta Total Compensation market benchmarks (salary, equity, total cash) for a role. Output to chat or CSV. Market benchmarks are triggered by queries like: "sales benchmarks", "comp benchmarks", "market rate", "what does a [role] pay", "put benchmarks in a CSV", "get benchmarks", "get carta's market…
carta-issuance
Issue securities on a Carta cap table. Use when the user asks to issue certificates, stock certificates, option grants (ISO, NSO, EMI, CSOP, Unapproved, Startup Concessions, Non-Concessional, ZEPO), to draft shares or grants, or to resume issuing from a draft set. USE WHEN the user says "issue", "grant", "draft"…
carta-consolidating-pnl
Consolidating P&L (Income Statement) across the entities of a firm, for any period the user picks — a month, quarter, year, or start-to-end date range. Produces TWO Excel tabs: detail P&L (Period + YTD Actual/Budget/Variance/%) and executive Summary P&L formula-linked to detail. Optional tag-view breaks Actuals down…
carta-compensation-scorecard
Carta Total Compensation scorecard — shows how a corporation's employees compare to market. Two lenses: corporation-level rollup (band distribution — what % of employees are below / at / above market) and per-employee scorecard (each employee's compa-ratio + percentile + market band). Triggered by queries like…
carta-compensation-rolematcher
Classify a job title or description into the CTC taxonomy (job area, focus, level, track). Use when the user wants to know how a role is categorized or mapped to the taxonomy structure — not to fetch salary, equity, or benchmark numbers. Do NOT use when the user is asking for "market rates", "benchmark data"…
carta-interaction-reference
Carta's behavioral rules for AI agents presenting cap table data — mandatory context for any Carta cap table response. Load ONCE per conversation, before the first such response (ownership, grants, SAFEs, valuations, waterfall scenarios, financing history, stakeholders, convertible instruments, option pools, or any…