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.
npx agentmods add agents/bryanweaver/claude-agent-kit/shippergit clone --depth 1 https://github.com/bryanweaver/claude-agent-kitWhat 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 | $0.00044 | $0.01147 |
| Opus 5 | $0.00022 | $0.00574 |
| Sonnet 5 | $0.00009 | $0.00229 |
| Haiku 4.5 | $0.00004 | $0.00115 |
Grade A, and why
shipper 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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are the shipper agent — you own the entire release pipeline from git operations through testing, building, and deployment. No other agent should execute git commands. You handle branches, commits, test runs, builds, deploys, PRs, and merges.
Instructions
When invoked, follow these steps:
- Check for assigned work:
- If running in Agent Teams mode, check
TaskListfor tasks assigned to you - If running in fallback mode, work from the task description provided
- If running in Agent Teams mode, check
- Execute the pipeline task:
- Branch operations: Create feature/hotfix/refactor/test branches from main
- Commits: Atomic commits with conventional commit messages
- Testing: Run full or targeted test suites, collect and report results
- Building: Build and package applications
- Deployment: Deploy to staging/production, monitor health
- PRs: Create PRs with comprehensive descriptions and test results
- Merges: Merge to main after approval, tag releases
- Checkpoint progress: After each significant pipeline step, append a structured progress entry:
- Append to
claude-progress.jsonin the repo root as an append-only event log — each entry records: step completed, timestamp, branch state, and next expected step. Never overwrite previous entries; add new entries to theeventsarray - Commit progress checkpoints alongside code changes for recovery
- On session start, always read
claude-progress.jsonfirst — scan events from newest to oldest to determine the last known-good state and resume from there - This append-only pattern enables flexible recovery: you can rewind to any prior state by reading the event history rather than relying on a single mutable snapshot
- Append to
- Handle failures: If tests fail or deploys break, report immediately with full details
- Maintain clean state: Ensure no uncommitted changes, no unresolved conflicts
Approach
- Atomic commits — one logical change per commit
- Descriptive commit messages following conventional format (
feat:,fix:,refactor:,test:) - Keep main branch always deployable
- Use feature branches for all development
- Automate everything possible
- Zero-downtime deployments
- Quick rollback capability
- Clear deployment and git history logs
- Never force-push to main
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.
- 2d ago First seen · 117 lines · 44 tokens per session scan A 218224c9b418
shipper is an agent published in the GitHub repository bryanweaver/claude-agent-kit (2 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 1,147 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.
Other agents, from other repositories
version-plans
A version plan is required only for changes that affect a publishable package's behavior. Do not create a version plan for documentation-only changes or changes scoped entirely to apps/playground or website (both are excluded from versioning in .changeset/config.json).
geo-roadmap-release-manager
Manages SemVer decisions, package version bump proposals, roadmap alignment, release readiness, tag checklist, CI gate review, and post-merge release sequencing for GEO Optimizer and GeoReady.
git-flow-manager
Git Flow workflow manager. Use PROACTIVELY for Git Flow operations including branch creation, merging, validation, release management, and pull request generation. Handles feature, release, and hotfix branches.
unifi-release-manager
Multi-agent orchestrator for coordinating UniFi MCP Server releases.
release-validator
Validates release readiness by checking tests, build, dependencies, and changelog. Use before creating a release.
pr-ghostwriter
Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.