researchforge-ship

researchforge-ship is a skill for Claude Code, Codex from forger-labs-hq/researchforge. It costs 45 tokens per session (759 once invoked), scanned A, original, Apache-2.0.

A shipping workflow for turning a validated experiment into a local code branch, an engineering report, or an optional pull request. A validated experiment is one that has passed the required repeated checks.

In plain words
What is it for?
Create one clean local commit, write a report containing the evidence and reproduction steps, or prepare an opt-in draft pull request.
Why use it?
It prevents unverified or constraint-breaking changes from being shipped and keeps the original checkout and remote repository safe until approval.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Create one clean local commit, write a report containing the evidence and reproduction steps, or prepare an opt-in draft pull request.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/forger-labs-hq/researchforge/researchforge-ship
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 forger-labs-hq/researchforge --skill researchforge-ship
Clone the repo
git clone --depth 1 https://github.com/forger-labs-hq/researchforge

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 researchforge-ship

README.md
[![agentmods](https://agentmods.dev/badge/skills/forger-labs-hq/researchforge/researchforge-ship/github.svg)](https://agentmods.dev/skills/forger-labs-hq/researchforge/researchforge-ship)
Your own site
<a href="https://agentmods.dev/skills/forger-labs-hq/researchforge/researchforge-ship"><img src="https://agentmods.dev/badge/skills/forger-labs-hq/researchforge/researchforge-ship/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 researchforge-ship

Your own site · 80×15
<a href="https://agentmods.dev/skills/forger-labs-hq/researchforge/researchforge-ship"><img src="https://agentmods.dev/badge/skills/forger-labs-hq/researchforge/researchforge-ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 759 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 $0.00045 $0.00759
Opus 5 $0.00023 $0.00380
Sonnet 5 $0.00009 $0.00152
Haiku 4.5 $0.00005 $0.00076

Measured 10d ago against content hash 8b9216c2ce3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

researchforge-ship 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 10d 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.

src/researchforge/claude/skills/researchforge-ship/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship a validated result

Three steps, each more outward-facing than the last. Every one is gated by the engine (contract flags + typed confirmations) and each gate exists for the user to open, not you.

1. Local branch (never pushed)

researchforge ship branch --json

Requires shipping.allow_branch_creation in the approved contract and a typed confirmation — ask the user to run it, or use --yes only with their explicit go-ahead in this conversation. The engine re-runs the full benchmark once (pre-ship confirmation) and refuses to ship on failure, constraint violation, or unconfirmed improvement. The result is one clean commit on the frozen baseline, as a local branch only — the user's checkout and remotes are untouched. Report the branch name, commit, and pre-ship metric from the JSON.

2. Engineering report

researchforge report build --json

Writes .researchforge/reports/engineering-report.md — the full evidence chain (objective → baseline → experiments → rejected approaches → validation → recommendation → exact reproduction steps), built from recorded data only. Offer to walk the user through it.

3. Draft PR (opt-in, pushes to the remote)

researchforge ship pr --json

This pushes one branch to the user's remote and opens a draft PR via gh. It is double opt-in: shipping.allow_draft_pr must be true in the approved contract AND a typed push confirmation is required. Confirm with the user in chat before this step every time; never use --yes here unless they just told you to push. If the contract flag is off, tell the user how to enable it (edit researchforge.yaml, re-approve the contract) — do not look for another way to push.

Open-source / third-party repositories — ask first. Before shipping a PR, ask the user how they relate to the repository:

  • They have push access (their own repo, or a repo they maintain): ship pr pushes a feature branch to it and opens the draft PR there.
  • They do not have push access (an open-source repo they cloned): the engine detects this, offers to fork into their GitHub account (typed fork confirmation — the user must type it), pushes the branch to the fork, and opens a cross-repo draft PR against the upstream. Never fork without that typed consent, and confirm which GitHub account gh is authenticated as (gh api user -q .login) so the fork lands where the user expects.

Read the full file on GitHub · 76 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. 10d ago First seen · 76 lines · 45 tokens per session scan A 8b9216c2ce3e

Subscribe to this mod's changes

researchforge-ship is a skill published in the GitHub repository forger-labs-hq/researchforge (8 stars, last pushed 7d ago), licensed Apache-2.0. It adds 45 tokens to every session and 759 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 2026-08-31.

Related

Other skills, from other repositories

cloudflare-workers-ci-cd

Complete CI/CD guide for Cloudflare Workers using GitHub Actions and GitLab CI. Use for automated testing, deployment pipelines, preview environments, secrets management, or encountering deployment failures, workflow errors, environment configuration issues.

secondsky/claude-skills · 50 tokens

claude-code-bash-patterns

Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.

secondsky/claude-skills · 52 tokens

definition-of-done

The ordered finish-line runner for any change in this repo — generators, then the asset-integrity refresh last on its own, then the full gate suite, then commit and push; use before declaring any change finished or whenever the stop hook reports uncommitted or untracked changes.

VincentChuWaiChow/vanguard-frontier-agentic · 61 tokens

pr-babysit

The repeatable loop for watching a pull request until it is merged or closed, pairing webhook subscription with a scheduled self check-in so CI results, new pushes, and merge-conflict transitions are never missed; use when asked to watch, babysit, or autofix a PR, or right after creating one.

VincentChuWaiChow/vanguard-frontier-agentic · 68 tokens

symlink-manager

Create, audit, repair, and document cross-platform symlinks that work correctly on both Windows and macOS/Linux. Use this skill whenever the user mentions symlinks, symbolic links, junction points, .gitconfig symlinks, broken links after git pull, cross-platform path issues, or needs help with ln -s equivalents on…

richfrem/agent-plugins-skills · 180 tokens

aws-ci-cd-release-engineer

Review AWS CI/CD and release safety across CodePipeline, CodeBuild, CodeDeploy, GitHub Actions, GitLab, artifact provenance, deployment gates, approvals, tests, progressive delivery, rollback, change correlation, and incident-prevention recommendations. Use when AWS releases or pipelines can affect production…

VincentChuWaiChow/vanguard-frontier-agentic · 69 tokens