Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add d-mariano/spicyclaude/plugin install spicy-shipWrote 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/d-mariano/spicyclaude/ship-pipeline)<a href="https://agentmods.dev/skills/d-mariano/spicyclaude/ship-pipeline"><img src="https://agentmods.dev/badge/skills/d-mariano/spicyclaude/ship-pipeline/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/d-mariano/spicyclaude/ship-pipeline"><img src="https://agentmods.dev/badge/skills/d-mariano/spicyclaude/ship-pipeline.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 | $0.00000 | $0.01994 |
| Opus 5.5 | $0.00000 | $0.00798 |
| Sonnet 5.5 | $0.00000 | $0.00399 |
| Haiku 4.5 | $0.00000 | $0.00199 |
Grade A, and why
ship-pipeline 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship pipeline
One story, five phases, two review loops. You orchestrate; you never do phase work yourself.
Every phase is a spicy-ship:phase:* agent that gets paths, writes an artifact, and ends with the
return envelope from question-policy. Your own context holds one line per phase and the
envelopes, nothing else.
Inputs
- The story: text plus acceptance criteria, already written to
story.mdin the context folder. - The context folder
/context/[nnn]-{slug}/. references/artifacts.md lists every file that lives there. ship-config.jsonin the context folder: the config resolved once at the start of the story. Agents get its path; the question mode comes from it, and the gate parameters are rendered from it withship_config.py --gate-flags=<phase> --from=<path>, never from a second resolution.
Phases
| # | Agent | Reads | Writes | Gate |
|---|---|---|---|---|
| 1 | spicy-ship:phase:explorer |
story.md |
research-[nnn].md |
none |
| 2 | spicy-ship:phase:planner |
story.md, research-[nnn].md |
plan-[nnn].md |
none |
| 3 | review loop: spicy-ship:phase:plan-reviewer and spicy-ship:phase:fixer in plan mode |
plan-[nnn].md, story.md |
plan-review-r{n}.json, plan-fixes-r{n}.json |
review.plan |
| 4 | spicy-ship:phase:executor |
plan-[nnn].md, research-[nnn].md, story.md |
commits, progress-[nnn].md |
none |
| 5 | review loop: spicy-ship:phase:code-reviewer and spicy-ship:phase:fixer in code mode |
base_sha..HEAD, story.md, plan-[nnn].md |
code-review-r{n}.json, code-fixes-r{n}.json |
review.code |
Phase 4 runs only when the plan gate's outcome proceeds per the review-loop outcomes table. Before
spawning the executor, record git rev-parse HEAD as base_sha in ship-state.json; every later
phase reviews base_sha..HEAD and nothing older, whatever else the branch carries.
Running a review loop
Follow review-loop exactly. Per round n:
- Spawn the reviewer with the target, the story, the round number, and for
n > 1the previous findings file and the previous fixes file. - Run the gate. Never guess its outcome, and never hand-copy the gate parameters: render them from the story's frozen config with one plain command, then paste the printed line into the gate call as a second plain command.
What ships with it
2 files 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.
- yesterday Changed · +10 lines 17833a4354da
- 2d ago Changed · +11 lines 3412478721b3
- 4d ago First seen · 111 lines · 0 tokens per session scan A dcecb0bf06e2
ship-pipeline is a skill published in the GitHub repository d-mariano/spicyclaude (5 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,994 tokens. 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 2026-11-07.
ship-pipeline compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ship-pipelined-mariano/spicyclaude | Skill | 5 | 2d ago | MIT | A | 0 | Claude Code |
| autoreviewopenclaw/clawhub | Skill | 9.6k | today | MIT | A | 17 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.5k | today | MIT | A | 49 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 115 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 953 | today | MIT | A | 84 | Claude Code |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | yesterday | MIT | A | 51 | Claude Code, Codex |
| explore-unknownsdzhng/skills | Skill | 1.5k | today | MIT | A | 162 | Claude Code, Codex |