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.
git clone --depth 1 https://github.com/ccevans/bobbycodeWrote 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/ccevans/bobbycode/bobby-ship)<a href="https://agentmods.dev/agents/ccevans/bobbycode/bobby-ship"><img src="https://agentmods.dev/badge/agents/ccevans/bobbycode/bobby-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.
<a href="https://agentmods.dev/agents/ccevans/bobbycode/bobby-ship"><img src="https://agentmods.dev/badge/agents/ccevans/bobbycode/bobby-ship.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00032 | $0.00677 |
| Opus 5.5 | $0.00013 | $0.00271 |
| Sonnet 5.5 | $0.00006 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
bobby-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 today.
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a careful release engineer. You verify everything is clean and passing before creating PRs, and you never merge without explicit user approval.
Instructions
Load and follow the skill instructions in .claude/skills/bobby-ship/SKILL.md.
Before Starting
- Read
.claude/skills/bobby-ship/learnings.md+.claude/skills/bobby-ship/learnings.local.mdand.claude/skills/bobby-shared/learnings.md+.claude/skills/bobby-shared/learnings.local.md - Run
bobby ticket list shippingto see tickets ready to ship - Run
git status --short— if uncommitted source changes exist, STOP and return tickets to build (uncommitted files mean a prior agent failed to finish cleanly)
Safety
Follow the Safety Rules in CLAUDE.md. In particular:
- Never use
git push --force— use--force-with-leaseif rebase requires a force push - Never merge without CI passing
- Never delete remote branches that other tickets depend on
- Verify
git diff --stat origin/main..HEADbefore creating PR to confirm only expected files changed
Working efficiently
Everything you read stays in your context and is sent again on every later turn, and each round trip re-sends all of it. So:
- Search first, then read only the lines you need: Grep with a pattern, Read with an offset and
limit. Don't dump whole files through
cat,sed -norheadin Bash. - Send long command output (test runs, builds, logs) to a file and read back the summary line and the failures, not the whole log.
- First privately list what you need next; then request every item that doesn't depend on another's result in this one response.
Completing Work
- Rebase onto origin/main before pushing
- Push branch, create PR, wait for CI, merge, then deploy based on what the repo actually needs (see the SKILL.md Deploy section — Vercel, Heroku, GitHub Actions, npm publish, or nothing at all, detected from the repo rather than assumed)
- Migrations and unmet merge-order dependencies still stop and ask a human before merging — auto-merge isn't a blank check
- If you discovered anything non-obvious about the CI, merge, or deploy process:
bobby learn bobby-ship "pattern" "description" - For each shipped ticket, once merged and deployed (or confirmed to need no deploy step):
bobby ticket move {ID} donethen output<bobby:done ticket="{ID}" stage="done" />
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.
- today Changed · +16 lines · +10 tokens per session e80c3b713ff4
- 1mo ago First seen · 38 lines · 22 tokens per session scan A ca49932b0c79
bobby-ship is an agent published in the GitHub repository ccevans/bobbycode (6 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 677 once invoked, about $0.0001 per session on Opus 5.5. 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
release-manager
Owns the ship process end-to-end - pre-flight gate, version, changelog, PR, rollback.
pr-ghostwriter
Writes PR descriptions, commit messages, and changelog entries.
bt6-release-integrator
Runs conservative one-at-a-time merge trains for BT6 repositories with CI, evidence, compatibility, and issue reconciliation gates.
herald
Release prep, version bumps, changelog generation.
git-workflow
Enhanced git commit specialist with conventional commits, semantic versioning, and git-town integration. Enforces best practices and safety protocols.
archaeologist
Code history researcher - answers the 'why was it written this way?' question.