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/ramantiz/planship/shipgit clone --depth 1 https://github.com/ramantiz/planshipWhat 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 | $0.00019 | $0.00802 |
| Opus 5 | $0.00010 | $0.00401 |
| Sonnet 5 | $0.00004 | $0.00160 |
| Haiku 4.5 | $0.00002 | $0.00080 |
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 2d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create GitHub milestones and issues from a planship PLAN.md.
Arguments: $ARGUMENTS — may contain a path to the plan (default PLAN.md), and optionally
--dry-run and/or --repo owner/name. Anything else in $ARGUMENTS is not a flag you invent;
pass through only the flags listed here.
You never construct gh commands yourself. ${CLAUDE_PLUGIN_ROOT}/scripts/ship-plan.mjs does
all GitHub work deterministically: it validates the plan, checks auth and permissions, previews,
creates idempotently, and resolves dependencies. Your job is to run it, show the user its output,
and gate the write behind an explicit confirmation.
Steps
-
Preview. Run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/ship-plan.mjs" <plan-path> --preview [--repo owner/name]This creates nothing. It stops with a clear message if
ghis missing or unauthenticated, if the repo is unreachable or read-only, or if the plan has structural errors (aBlocked bythat names no real task, a cycle, duplicate titles). -
If it exited non-zero: show the user the error verbatim and stop. Do not attempt to fix the repo, re-auth, or work around it. If the failure is a plan error, suggest
/planship:review <plan>. Nothing has been created — say so. -
Show the preview output to the user verbatim. Do not summarize it away; the target
owner/repoand the create/skip list are exactly what they are being asked to approve. -
If
--dry-runwas passed: stop here. Say that this was a dry run and nothing was created, and that they can run the same command without--dry-runto create. -
If there is nothing to create (0 issues and 0 milestones): say so and stop.
-
Otherwise, ask for confirmation and END YOUR TURN. Ask exactly:
Create N issues and M milestones in owner/repo? [y/N]
Then stop. Do not call any tool. Do not proceed. Wait for the user's actual reply.
-
Only after the user replies affirmatively (
y,yes,ship it— anything ambiguous is a no), run:node "${CLAUDE_PLUGIN_ROOT}/scripts/ship-plan.mjs" <plan-path> --apply [--repo owner/name]Show its final table (number · title · milestone · url) to the user.
If the user declines, confirm that nothing was created and stop.
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.
- 2d ago First seen · 69 lines · 19 tokens per session scan A fc43e852e60b
ship is a command published in the GitHub repository ramantiz/planship (10 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 802 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.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.