pre-push

pre-push is a skill for Claude Code, Codex from onsager-ai/dev-skills. It costs 47 tokens per session (849 once invoked), scanned A, original, MIT.

A pre-push checklist for repositories that use specification-driven development, where an issue describes the work before coding begins. It checks the branch and runs the repository’s required checks before code is pushed.

In plain words
What is it for?
Use it before pushing code to verify the repository’s check command, inspect likely conflict points, and confirm the branch is tied to a valid specification issue.
Why use it?
It catches problems locally before CI or reviewers find them, including missing links to the issue that specifies the work and common merge conflicts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Use it before pushing code to verify the repository’s check command, inspect likely conflict points, and confirm the branch is tied to a valid specification issue.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/onsager-ai/dev-skills/pre-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 onsager-ai/dev-skills --skill pre-push
Clone the repo
git clone --depth 1 https://github.com/onsager-ai/dev-skills

Made for: Claude Code, Codex.

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 pre-push

README.md
[![agentmods](https://agentmods.dev/badge/skills/onsager-ai/dev-skills/pre-push/github.svg)](https://agentmods.dev/skills/onsager-ai/dev-skills/pre-push)
Your own site
<a href="https://agentmods.dev/skills/onsager-ai/dev-skills/pre-push"><img src="https://agentmods.dev/badge/skills/onsager-ai/dev-skills/pre-push/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pre-push

Your own site · 80×15
<a href="https://agentmods.dev/skills/onsager-ai/dev-skills/pre-push"><img src="https://agentmods.dev/badge/skills/onsager-ai/dev-skills/pre-push.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 849 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.
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 $0.00047 $0.00849
Opus 5.5 $0.00019 $0.00340
Sonnet 5.5 $0.00009 $0.00170
Haiku 4.5 $0.00005 $0.00085

Measured 15d ago against content hash f2371605bc3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pre-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 15d 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.

skills/pre-push/SKILL.md · 71 lines

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.

Pre-push

Scope

This skill owns integration and publication readiness. AGENTS.md and the repo workflow overlay own workspace isolation, the intended base, gate commands, warning severity and whether a spec link or trivial exception is required. Availability of this skill grants no push, PR or merge authority.

Prerequisites

Inspect branch, worktree and working-tree state before edits. Preserve unrelated changes and keep primary-checkout parking rules intact. Resolve the actual remote and base branch, which may differ from main. Load harness-operations if a tool mapping is needed.

Procedure

  1. Inspect the current diff and intended base. Refresh that base through the configured remote and record its SHA. If fetching is blocked, report that the base/merge gate could not be verified; do not claim offline integration success.
  2. Follow the repo's integration route. If its gate builds a committed merge preview itself, satisfy its clean-tree prerequisite and run that gate without replacing it with a manual branch check. Otherwise merge the intended base in the task worktree when required; avoid rewriting published history or forcing a push.
  3. Resolve conflicts locally. Inventory unresolved paths, reconcile all changed intents, stage resolutions and run relevant gates before completing the merge. Preserve changelog/registry entries from both sides. Regenerate lockfiles and generated assets with their owning tools; do not hand-edit them. For shared documents reconcile section intent. Abort an unsuccessful merge only when it preserves the pre-merge work; never discard unrelated changes.
  4. Run exactly the repository's mandatory gates and diff-conditional checks on the required tree. Respect its distinction between advisory and blocking warnings. Missing tooling, origin access or environment setup is blocked validation, not a pass. Do not suppress failures, weaken assertions or bypass hooks. Once the required checks pass, repeat them only for changed inputs, a new failure or an unresolved concern. Missing optional tooling does not block independent work or reviewable PR preparation; describe its validation limit.
  5. Apply the declared contribution process. Where SDD is required, verify a spec exists, its blocking decisions are resolved, and the proposed PR links the right delivery slice. Use issue-spec for missing specs. Where a trivial exception is allowed, justify it using the repo's definition. Reconcile issue references in commits deliberately; incidental mentions do not imply closure. A repository without this gate acquires none from this skill.
  6. When publication is authorized, publish the validated branch with the available Git transport or connected GitHub API. On transport failure use an available authenticated equivalent; when publishing trees through an API, preserve modes, deletions and parent lineage and verify exact tree identity. Do not force-update a protected/long-lived branch. Limited retries are appropriate for transient errors; authorization errors require capability diagnosis, not repeated retries.
  7. Hand PR creation/update and its check sweep to pr-lifecycle.

Read the full file on GitHub · 71 lines

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. 15d ago Changed · +3 lines f2371605bc3c
  2. 18d ago Changed · -60 lines · -120 tokens per session fb5831be5f4c
  3. 1mo ago First seen · 128 lines · 167 tokens per session scan A f4e44b5d1e1b

Subscribe to this mod's changes

pre-push is a skill published in the GitHub repository onsager-ai/dev-skills (7 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 849 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.