What is alpha-forge-preship?

A set of quality checks for reviewing Alpha Forge pull requests, which are proposed code changes. The checks cover random-number repeatability, fork URLs, parameter ranges, and synchronisation between a code manifest and its YAML configuration.

Use it to validate Alpha Forge changes through pre-commit and CI checks and to run the checks through one coordinator.

It catches specific mistakes before changes are accepted or run, including checks that can be used during commits or continuous integration.

alpha-forge-preship — Skill for Claude Code by terrylica

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 terrylica/cc-skills --skill alpha-forge-preship

Clone the repo

git clone --depth 1 https://github.com/terrylica/cc-skills

Made for: Claude Code.

Or install quality-tools, the plugin that ships this one along with the rest of its 11 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/terrylica/cc-skills/alpha-forge-preship/github.svg)](https://agentmods.dev/skills/terrylica/cc-skills/alpha-forge-preship)

Your own site

<a href="https://agentmods.dev/skills/terrylica/cc-skills/alpha-forge-preship"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/alpha-forge-preship/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/terrylica/cc-skills/alpha-forge-preship"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/alpha-forge-preship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 700 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 warn 7 Sept 2026

SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Rogue Agent · line 88
Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00027	$0.00700
Opus 5	$0.00014	$0.00350
Sonnet 5	$0.00005	$0.00140
Haiku 4.5	$0.00003	$0.00070

Measured 7d ago against content hash cc589f96ebc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

alpha-forge-preship 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 7d ago.

The scan reads SKILL.md. This mod also ships 23 executable files (gates/__init__.py, gates/g1_documentation_scope.py, gates/g10_performance_red_flags.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/quality-tools/skills/alpha-forge-preship/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Alpha Forge Pre-Ship Quality Gates - Phase 1

Quality assurance plugin for Alpha Forge PR review cycle.

Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.

Overview

Implements 4 bulletproof quality gates to catch 5 of 13 PR #154 issues:

G5: RNG Determinism (pre-commit)
G4: URL Fork Validation (pre-commit)
G8: Parameter Validation (runtime/CI)
G12: Manifest Sync Validation (CI)

Effectiveness

Issue Prevention: 42% of PR issues
False Positive Rate: <1%
Implementation Time: ~4 hours
Payoff Period: 2-3 PRs
Review Cycle Reduction: 30-50%

Key Files

gates/g5_rng_determinism.py - RNG isolation validator
gates/g4_url_validation.py - Fork URL detector
gates/g8_parameter_validation.py - Parameter range validator
gates/g12_manifest_sync.py - Decorator-YAML sync validator
orchestrator.py - Master validator coordinator
reference.md - Complete framework documentation

Architecture

All gates enforce the Decorator-as-Single-Source-of-Truth principle:

Parameter constraints defined in decorators
Configuration validated at entry points
Manifest consistency ensured automatically
Documentation requirements enforced systematically

Integration

Pre-Commit Hook

from gates.g4_url_validation import validate_org_urls
from gates.g5_rng_determinism import validate_rng_isolation

Runtime Parameter Validation

from gates.g8_parameter_validation import ParameterValidator
validator = ParameterValidator()
validator.validate_numeric_range(value, min_val, max_val)

Manifest Validation

from gates.g12_manifest_sync import validate_manifest
issues = validate_manifest("manifest.yaml")

References

Main Handbook: /tmp/CANONICAL_PRESHOP_AUDIT_HANDBOOK.md (523 lines)
Implementation Plan: /tmp/PHASE_1_IMPLEMENTATION_PLAN.md (367 lines)
Project Summary: /tmp/PROJECT_COMPLETION_SUMMARY.md

Read the full file on GitHub · 91 lines

Files

What ships with it

26 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

7d ago First seen · 91 lines · 27 tokens per session scan A cc589f96ebc3

Subscribe to this mod's changes

alpha-forge-preship is a skill published in the GitHub repository terrylica/cc-skills (73 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 700 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 2026-09-05.

Claude Code Git and workflow Testing ai-tools anthropic automation claude clickhouse

github-release-management

GitHub release orchestration — automated versioning, testing, deployment, and rollback. Use when cutting a release, tagging a version, drafting release notes, or coordinating a deploy/rollback workflow.

frankxai/claude-skills-library · 43 tokens

accessibility-a11y

WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.

travisjneuman/.claude · 26 tokens

core-workflow

Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, testing, or when explicit patterns are needed. Contains session protocols, git conventions, security checklists, testing strategy, and communication standards.

travisjneuman/.claude · 53 tokens

alpha-forge-preship