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 skills add r13v/pi-feature-dev --skill shipgit clone --depth 1 https://github.com/r13v/pi-feature-devWrote 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/skills/r13v/pi-feature-dev/ship)<a href="https://agentmods.dev/skills/r13v/pi-feature-dev/ship"><img src="https://agentmods.dev/badge/skills/r13v/pi-feature-dev/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/skills/r13v/pi-feature-dev/ship"><img src="https://agentmods.dev/badge/skills/r13v/pi-feature-dev/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 | $0.00111 | $0.04766 |
| Opus 5.5 | $0.00044 | $0.01906 |
| Sonnet 5.5 | $0.00022 | $0.00953 |
| Haiku 4.5 | $0.00011 | $0.00477 |
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 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 — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship
Take one non-trivial implementation request through the full pipeline:
[elevate] → grill → [deepen] → feature-dev → deslop → [final-check] → [retro]
This skill only orchestrates. Each stage follows its own skill. This skill selects the stages, passes each result to the next stage, and keeps the approval points of each stage. Ship ends with validated changes in the working tree. Do not commit, push, publish, or deploy unless the user asks.
When a stage starts, load the skill of that stage and follow it, even when an earlier run in the same session loaded it. A stage that ran from memory is not done. Talk to the user in the language of the request. The formats in the skills fix the structure, not the words.
Check the request first
Use ship only for non-trivial implementation. If the request is a mechanical edit, a small fix, or work with no implementation, such as a report or an analysis, do not run the pipeline. Name the shorter path that fits, such as a direct edit or one skill, and stop. If the host started ship without the user asking for it, propose ship and wait.
If the request is the path of a backlog item under docs/backlog/, read the
item as the backlog skill describes. Check its where and its evidence
against the current code. Measure the claim of the evidence again before you
call the item stale. If only its where is out of date, update it and
continue. If the item is stale or the idea is already done,
offer to drop it as the backlog skill describes, and then stop. If its worth
is no, give the
reason from the item and ask whether to continue. Otherwise, use the item as
the original request. It is an idea to grill, not a settled specification.
Write the path of the item in the progress file. Delete the item file during
feature-dev, as a change of this task.
Keep a progress file
Keep the state of the pipeline in a progress file, not only in the conversation. The file prevents skipped stages and lets the work continue after the context is compacted or in a new session in the same checkout.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · +80 lines a98eed1b4f8b
- 9d ago Changed · +85 lines · +26 tokens per session 0fda31839776
- 10d ago First seen · 213 lines · 85 tokens per session scan A 058b39ef7f88
ship is a skill published in the GitHub repository r13v/pi-feature-dev (3 stars, last pushed 2d ago), licensed MIT. It adds 111 tokens to every session and 4,766 once invoked, about $0.0004 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 2026-10-22.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…
remove
Remove a deployed framework or addon from the current workspace.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…