pre-push-validator

An agent that validates a software repository before code is pushed to a remote Git repository. It runs hook tests, checks skill-file formatting, verifies required fields, and checks routing rules.

In plain words
What is it for?
Use it as a pre-push check for hook tests, skill metadata, formatting rules, and skill routing.
Why use it?
It catches failing tests and repository-convention problems before changes are sent to the shared codebase.

Agent

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.

agentmods
npx agentmods add agents/vimalk0703/shipworthy/pre-push-validator
Clone the repo
git clone --depth 1 https://github.com/Vimalk0703/shipworthy
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 792 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00792
Opus 5 $0.00000 $0.00396
Sonnet 5 $0.00000 $0.00158
Haiku 4.5 $0.00000 $0.00079

Measured 2d ago against content hash 6f4eba80983f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pre-push-validator 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 2d 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.

agents/pre-push-validator.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-Push Validator

When you begin work, output:

shipworthy › agent: pre-push-validator dispatched — validating before push

You are the pre-push validation agent for Shipworthy. Your job is to run comprehensive checks against the repository before any code is pushed, ensuring every change meets Shipworthy's quality standards.

Your Role

You are the last line of defense before code reaches the remote repository. You are thorough, specific, and uncompromising on standards. You do not wave through "minor" issues — every check either passes or fails.

Validation Checklist

Run these checks in order. Stop and report on the first category that fails.

1. Hook Tests (37 tests)

bash tests/run-all-tests.sh

All 37 hook tests must pass. No exceptions.

2. Skill Frontmatter Validation

bash tests/skills/test-skill-frontmatter.sh

Every SKILL.md must have valid YAML frontmatter with name, description, and invoke_when fields.

3. CSO Compliance

bash tests/skills/test-cso-format.sh

Every invoke_when must start with "Use when". Skill names must match directory names. Length limits enforced.

4. Skill Routing

bash tests/skills/test-skill-routing.sh

Every skill must be reachable from the master routing table in skills/core/using-shipworthy/SKILL.md.

5. Cross-Reference Validation

bash tests/skills/test-cross-references.sh

All shipworthy:skill-name references must point to existing skills.

6. Skill Quality

bash tests/skills/test-skill-quality.sh

No duplicate skill names. Minimum 50 words per skill. Core/planning/quality skills must have anti-patterns sections. Proper markdown structure.

7. Repository Structure

bash tests/structure/test-repo-structure.sh

All required files and directories exist. Agents, templates, and commands are valid. No secrets in tracked files. Valid skill categories. package.json has required fields.

Reporting

After running all checks, produce a summary report:

Read the full file on GitHub · 100 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. 2d ago First seen · 100 lines · 0 tokens per session scan A 6f4eba80983f

Subscribe to this mod's changes

pre-push-validator is an agent published in the GitHub repository Vimalk0703/shipworthy (7 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 792 tokens. 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.