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 commands/stefanhoelzl/codehydra/shipgit clone --depth 1 https://github.com/stefanhoelzl/codehydraWrote 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.
[](https://agentmods.dev/commands/stefanhoelzl/codehydra/ship)<a href="https://agentmods.dev/commands/stefanhoelzl/codehydra/ship"><img src="https://agentmods.dev/badge/commands/stefanhoelzl/codehydra/ship.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00014 | $0.02951 |
| Opus 5 | $0.00007 | $0.01476 |
| Sonnet 5 | $0.00003 | $0.00590 |
| Haiku 4.5 | $0.00001 | $0.00295 |
Grade A, and why
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 4d 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 — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ship Command
Ship the current branch by creating a PR with auto-merge and waiting for it to merge.
Arguments
$ARGUMENTS
- Empty: Auto-generate PR title and summary from commits
featorfix: User-facing change. Agent proposes a PR title, user reviews.feat(<title>)orfix(<title>): User-facing change with explicit PR title.internal: Internal change (no changelog entry). Skips user-facing detection.--keep-workspace: Keep workspace after successful merge (default: delete)--resolves <issue>: Link PR to a GitHub issue--resolves #123or--resolves 123: Links to issue #123--resolves ?: List all open issues and prompt for selection
Execution
You are a BUILD AUTOMATION agent. Execute the workflow below. On FAILED or TIMEOUT, return immediately with a report - do NOT attempt to diagnose or fix issues.
1. Basic preconditions
1.1. Check for uncommitted changes:
git status --porcelain
If output is non-empty: ABORT with:
Cannot ship with uncommitted changes.
**Uncommitted files:**
<list of files>
Commit your changes first, then run `/ship` again.
1.2. Check we're not on main:
git branch --show-current
If on main: ABORT with "Cannot ship from main branch"
2. Check if already pushed
git fetch origin
Compare local HEAD with the remote tracking branch:
git rev-parse HEAD
git rev-parse origin/<current-branch>
If the remote branch exists and both SHAs match: skip to step 5 (check for existing PR).
If the remote branch does not exist or the SHAs differ: continue to step 3.
3. Local checks (skipped when already pushed)
3.1. Check formatting:
pnpm format:check
If formatting check fails: ABORT with:
Cannot ship with formatting issues.
Run `pnpm format` to fix, then commit and run `/ship` again.
3.2. Check application logs:
Find the most recent .log file in app-data/logs/ (sorted by filename, which is timestamp-based).
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.
- 4d ago First seen · 399 lines · 14 tokens per session scan A ed104c85791b
ship is a command published in the GitHub repository stefanhoelzl/codehydra (20 stars, last pushed 6d ago), licensed MIT. It adds 14 tokens to every session and 2,951 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 2026-08-30.
Other commands, from other repositories
docs-builder
Reorg a docs corpus, split an oversized doc, search it, keep pages current, index them.
live-canvas
Conduct design interviews, generate UI variations, and collect live click-to-annotate feedback that streams into the session so edits land without leaving the browser. Use when the user wants rapid iterative UI refinement, not just batched feedback.
remember
Consolidate stashes + friction into project memory.
debug-method
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
tdd-flow
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first.