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/w2ur/claude-code-setupWrote 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/w2ur/claude-code-setup/ship-plan)<a href="https://agentmods.dev/commands/w2ur/claude-code-setup/ship-plan"><img src="https://agentmods.dev/badge/commands/w2ur/claude-code-setup/ship-plan/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/commands/w2ur/claude-code-setup/ship-plan"><img src="https://agentmods.dev/badge/commands/w2ur/claude-code-setup/ship-plan.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 | $0.00038 | $0.00856 |
| Opus 5.5 | $0.00015 | $0.00342 |
| Sonnet 5.5 | $0.00008 | $0.00171 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
ship-plan 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 21d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This command adds only the sequencing and the approval stop. It owns no review logic and
no execution logic: each step hands off to the skill named below, which does that work its
own way. The model of each step is named here so routing does not depend on the prompt; the
tiers themselves come from the Sub-agents section of ~/.claude/CLAUDE.md.
$0 is the plan path. If it is empty, or not a .md file under ~/.claude/plans/, stop
and ask — plans never live in a repo, and a *-review.md file is not a plan.
Step 1 — review (opus)
Invoke the plan-reviewer:plan-review skill on $0. $0 overrides the skill's
"most recently modified plan" default — name the path explicitly. It writes
~/.claude/plans/<plan-name>-review.md with MUST / SHOULD / CONSIDER sections.
Before going on, confirm that review file exists and is newer than the plan. A missing or stale review file means the review did not run; stop and say so.
Step 2 — fold MUST and SHOULD (opus)
Snapshot the plan first, so Step 3 can show exactly what changed:
p="$0"; p="${p/#\~/$HOME}"
cp "$p" "${TMPDIR:-/tmp}/ship-plan-$(basename "$p" .md).before.md"
Then fold every MUST and SHOULD item into the plan, on opus: deciding the replacement text is judgment, not execution. Owner decisions are not re-litigated. When a finding contradicts a decision the plan records, do not fold it — list it for the owner instead. CONSIDER items are the owner's call; list them, fold none.
Step 3 — STOP: show the plan diff and wait for approval
p="$0"; p="${p/#\~/$HOME}"
diff -u "${TMPDIR:-/tmp}/ship-plan-$(basename "$p" .md).before.md" "$p"
Show that diff, then the unfolded items from Step 2 (decision conflicts and CONSIDER). Stop here and wait for the owner's explicit approval. Do not start Step 4 in the same turn. If the owner amends the plan, re-show the diff and wait again.
Step 4 — execute (per the tier table)
- Three or more independent targets → a Workflow; load the
workflow-authoringskill first. - Otherwise → the
superpowers:subagent-driven-developmentskill.
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.
- 21d ago First seen · 71 lines · 38 tokens per session scan A 17d08c90d52c
ship-plan is a command published in the GitHub repository w2ur/claude-code-setup (2 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 856 once invoked, about $0.0002 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 2026-09-26.
Other commands, from other repositories
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
phase
Orchestrate a full roadmap phase. Designs features, imports to tracker, creates issues, then executes.
dashboard
Compact visual progress dashboard with progress bar, task table, dependency graph, and active/blocked/next status.
plan-start
5-phase planning command: PRD analysis, design review, technical decisions, dynamic research team, metrics. Produces a complete implementation plan + ADRs before any code is written.
status
Show current execution status with progress, dependencies, file ownership, and parallelization opportunities.
sync
Reconcile coco tracker state with the configured issue tracker. Syncs task statuses and reports mismatches.