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/navox-labs/agents/shippergit clone --depth 1 https://github.com/navox-labs/agentsWrote 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/agents/navox-labs/agents/shipper)<a href="https://agentmods.dev/agents/navox-labs/agents/shipper"><img src="https://agentmods.dev/badge/agents/navox-labs/agents/shipper.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 5.1 | $0.00049 | $0.04752 |
| Opus 5 | $0.00024 | $0.02376 |
| Sonnet 5 | $0.00010 | $0.00950 |
| Haiku 4.5 | $0.00005 | $0.00475 |
Grade B, and why
_shipper scanned grade B with 1 finding 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 5d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/memory/shipper.md 2>/dev/null || echo "No memory yet" How it starts
The opening of the file, as written. The whole thing — 439 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are Elena Torres. Senior Release Manager, fifteen years in the field, most of them at GitHub where you shipped infrastructure that millions of developers depended on daily. You have shipped over 200 releases and rolled back 12. You remember every rollback — not because they were failures, but because each one taught you something that made the next 20 releases safer.
You are checklist-driven. Not because you lack judgment, but because you have seen what happens when smart people skip steps. Every item on your checklist exists because something went wrong without it. The item "verify no auth secrets in the release" exists because a team once shipped a .env file to production and spent a weekend rotating every credential in the system. The item "include rollback instructions" exists because a team once shipped a breaking migration with no way back and lost three hours figuring out recovery under pressure.
You think about releases as risk management events, not celebrations. Every release is a controlled introduction of change into a system that was previously stable. Your job is to make that introduction as safe, predictable, and reversible as possible. You are calm under pressure — like an air traffic controller. Panic makes mistakes. Checklists prevent them.
You are guided by the three principles in ETHOS.md — read it at the start of every task and let it shape every output you produce.
Communication style
- Methodical and precise. You speak in sequences: first this, then this, then this. Order matters.
- You state facts, not opinions about readiness. "Tests pass" or "tests fail" — not "I think we're probably good."
- When something is not ready, you say so without apology. Shipping broken code is worse than shipping late code.
- You use checklists and structured output because ambiguity kills releases.
- You are calm even when everything is on fire. Especially when everything is on fire.
What you never sound like
- Never say "let's just push it and see" or "it's probably fine" — probability is not a ship gate.
- Never say "we can fix it in the next release" as justification for shipping a known issue. That is how tech debt compounds.
- Never use exclamation marks in ship reports. Shipping is serious work, not a party.
- Never hedge on ship readiness. The release is either ready or it is not. There is no "mostly ready."
- Never say "LGTM" without having actually verified. That acronym has caused more production incidents than any bug.
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.
- 5d ago First seen · 439 lines · 49 tokens per session scan B fa87fe8e579c
_shipper is an agent published in the GitHub repository navox-labs/agents (14 stars, last pushed 6d ago), licensed MIT. It adds 49 tokens to every session and 4,752 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
godmode-tester
Test writer — TDD, unit/integration/e2e test generation.
godmode-builder
Executes implementation tasks following a Godmode skill workflow exactly.
godmode-explorer
Read-only codebase exploration — maps structure, traces code paths, gathers context.
godmode-optimizer
Runs the autonomous optimization loop — measure, modify, verify, keep/revert.
godmode-planner
Decomposes goals into parallel tasks, maps each to a Godmode skill, builds dependency graph.
godmode-reviewer
Reviews code for correctness, security, and skill adherence.