exec-push

exec-push is a skill for Claude Code from blockmatic/basilic. It costs 30 tokens per session (368 once invoked), scanned A, original, MIT.

A workflow tool that carries out a plan, checks the result, creates a Git commit, pushes it to a remote repository, and opens a pull request. A pull request is a request for others to review and merge changes.

In plain words
What is it for?
Use it to execute planned development work, validate it, publish the commit, and create a pull request.
Why use it?
It combines the routine steps after implementation so changes can move from local work to team review in one workflow.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to execute planned development work, validate it, publish the commit, and create a pull request.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/blockmatic/basilic/exec-push
Install

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.

Any agent
npx skills add blockmatic/basilic --skill exec-push
Clone the repo
git clone --depth 1 https://github.com/blockmatic/basilic

Made for: Claude Code.

Wrote 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.

agentmods badge for exec-push

README.md
[![agentmods](https://agentmods.dev/badge/skills/blockmatic/basilic/exec-push.svg)](https://agentmods.dev/skills/blockmatic/basilic/exec-push)
Your own site
<a href="https://agentmods.dev/skills/blockmatic/basilic/exec-push"><img src="https://agentmods.dev/badge/skills/blockmatic/basilic/exec-push.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 368 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.00368
Opus 5 $0.00015 $0.00184
Sonnet 5 $0.00006 $0.00074
Haiku 4.5 $0.00003 $0.00037

Measured yesterday against content hash 4b2297ef8b01, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

exec-push 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.

.agents/skills/workflow/exec-push/SKILL.md · 26 lines

What it actually says

Purpose and inputs

Invocation requests the complete implementation-to-PR path. Read the task or plan, repository instructions, branch state, affected docs, and scripts. Do not broaden the request to merge or deployment.

Steps

  1. Inspect the working tree and current branch. If a new branch is needed, use the repository naming convention and preserve uncommitted work; do not blindly pull into a dirty checkout.
  2. Implement and review the requested change in complete slices using build.
  3. Update affected technical docs and nearest README. Run the repository's full pre-push gate (pnpm qa in Basilic); diagnose failures before publishing.
  4. Commit task-owned changes with git-commit, then push with git-push.
  5. Create or update the PR with git-create-pr. Use the repository PR template. Preserve a BREAKING CHANGE: footer in the body when the title uses ! (squash uses PR_TITLE + PR_BODY). Never open an empty description.

Verification and handoff

  • Requested acceptance criteria and required validation pass.
  • Commit and push contain only intended work, with hooks enabled.
  • PR targets the correct base and explains the final behavior.

Return the commit, branch, PR link, and checks. If a gate fails, report the blocker and the completed local work; do not present an unpublished change as shipped.

Changes

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.

  1. yesterday Changed · +10 lines 4b2297ef8b01
  2. 4d ago First seen · 16 lines · 30 tokens per session scan A 33aa42e838d7

Subscribe to this mod's changes

exec-push is a skill published in the GitHub repository blockmatic/basilic (89 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 368 once invoked, about $0.0002 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.