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/wittyreference/twilio-claude-plugin/shipgit clone --depth 1 https://github.com/wittyreference/twilio-claude-pluginWhat 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 | $0.00028 | $0.00970 |
| Opus 5 | $0.00014 | $0.00485 |
| Sonnet 5 | $0.00006 | $0.00194 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
ship scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship It
Full lifecycle: commit → push → PR → CI → merge → exit worktree. The "I'm done, land it" command.
Prerequisites
1. Worktree Check
BRANCH=$(git branch --show-current)
If the branch is main, warn: "/ship is designed for worktree branches. Use /commit + /push for main, or start a worktree with /worktree-start."
2. gh CLI
gh auth status
If not authenticated, tell the user to run ! gh auth login.
Phase 1: Commit (if needed)
Check for uncommitted changes:
git status --porcelain
If there are staged or modified tracked files, run the /commit workflow:
- TypeScript check (if applicable):
cd agents/mcp-servers/twilio && npx tsc --noEmit - Test suite:
npm test --bail - ABOUTME comments on new files
- Stage and commit with conventional message
If the user provided arguments (e.g., /ship fix the ngrok port), use them as commit message context.
If there are no uncommitted changes, skip to Phase 2.
Phase 2: Push and PR
Push the branch
git push -u origin "$BRANCH"
Check for existing PR
gh pr view --json number,state,url 2>/dev/null
If a PR already exists and is open, skip to Phase 3.
Create PR
Generate title and body from the commits on this branch:
COMMITS=$(git log --oneline origin/main.."$BRANCH" 2>/dev/null || git log --oneline main.."$BRANCH")
gh pr create \
--title "<conventional commit title>" \
--body "<body>" \
--base main
Body includes:
## What— brief description## Why— motivation from commit messages- Commit list if multi-commit
Phase 3: Wait for CI
Enable auto-merge so we don't need to poll:
gh pr merge <pr-number> --auto --merge
Then check current CI status once:
gh pr checks <pr-number>
Report the status:
- All passed + auto-merge enabled → "PR will merge automatically when branch protection is satisfied."
- Checks still running → "Auto-merge enabled. CI is running — PR will merge when checks pass."
- Any failed → Report failures and stop. Do NOT exit the worktree on failure.
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.
- yesterday First seen · 155 lines · 28 tokens per session scan A 2980dba68be3
ship is a command published in the GitHub repository wittyreference/twilio-claude-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 970 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.