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 skills/shipwrights/core/shipwrights-loopnpx skills add shipwrights/core --skill shipwrights-loopgit clone --depth 1 https://github.com/shipwrights/coreWhat 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 | $0.00077 | $0.03208 |
| Opus 5 | $0.00039 | $0.01604 |
| Sonnet 5 | $0.00015 | $0.00642 |
| Haiku 4.5 | $0.00008 | $0.00321 |
Grade A, and why
shipwrights-loop 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/shipwrights-loop — sequential multi-ticket pipeline driver
Composes /shipwrights-epic end-to-end across N tickets. Picks one, drives it through the pipeline, watches the PR for merge, hands off Jira status, picks the next.
Not autopilot. Each PR still goes through whatever review gate is configured (human or tier:* auto-merge label). The loop watches — it doesn't merge.
Inputs
/shipwrights-loop [N]— start a new loop or resume an existing one.N= max iterations. Omit for unbounded (a confirmation prompt fires first)./shipwrights-loop --status— print current loop state, do nothing else./shipwrights-loop --abort— discard.shipwrights/loop-state.json, cancel any in-progress polling.
State machine
State lives in .shipwrights/loop-state.json (gitignored). Read/write via lib/loop-state.mjs. Phases:
| Phase | Meaning |
|---|---|
between_epics |
About to pick a new ticket. Initial state. |
running_epic |
/shipwrights-epic is mid-pipeline. Per-epic progress lives in the epic file's frontmatter + the in-flight register, not here. |
awaiting_merge |
PR opened, polling gh pr view <num> for MERGED. |
done |
Terminal. Either iteration cap hit, backlog empty, or user aborted. |
Valid transitions:
between_epics → running_epic | donerunning_epic → awaiting_merge | between_epics | doneawaiting_merge → between_epics | done
Auto-merge warning
When loop.auto_merge: true in .shipwrights.yml and the loop is starting fresh, print this verbatim before the typed-confirmation prompt. Don't reword it — the wording is the safety mechanism.
⚠ AUTO-MERGE ENABLED
With this turned on, /shipwrights-loop will MERGE pull requests itself.
Every PR opened during this loop will be merged automatically once your
required CI checks pass. No human review. No manual gate.
This means:
• Code reaches your integration branch without a human reading it
• Branch-protection rules still apply (required checks, required
reviewers if configured)
• Cost-cap and stuck-PR safeguards still apply
• The `do-not-auto-merge` label on a specific PR still skips auto-merge
for it
• Once you confirm, this loop runs unattended until done, aborted,
a PR is declined, or a safeguard fires
To confirm, type exactly: yes auto-merge
To cancel, type anything else.
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 · 192 lines · 77 tokens per session scan A 9cf16c392768
shipwrights-loop is a skill published in the GitHub repository shipwrights/core (2 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 3,208 once invoked, about $0.0004 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 skills, from other repositories
rtk-triage
Triage complet RTK : exécute issue-triage + pr-triage en parallèle, puis croise les données pour détecter doubles couvertures, trous sécurité, P0 sans PR, et conflits internes. Sauvegarde dans claudedocs/RTK-YYYY-MM-DD.md. Args: "en"/"fr" pour la langue (défaut: fr), "save" pour forcer la sauvegarde.
campaign-conductor
Run a project as an orchestrated campaign: Claude as conductor (Fable, or Opus when Fable is unavailable) dispatching a mixed fleet of workers, Claude Opus agents for UI/UX and design judgment, OpenAI Codex CLI workers for implementation and everything else. Use whenever the user says "start a campaign", "campaign…
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
trigger-authoring-tasks
Covers writing backend Trigger.dev tasks with @trigger.dev/sdk: defining task() and schemaTask(), the run function and its ctx, retries, waits, queues and concurrency, idempotency keys, run metadata, logging, triggering other tasks (and the Result shape), scheduled/cron tasks, and the essentials of trigger.config.ts.…
background
Use when the user wants to see, inspect, cancel, or prune background agents fired during prior chain runs. Read/manage .hyperflow/background/registry.json and the per-agent output buffers at .hyperflow/background/ .md. Standalone — never auto-invoked. Trigger with /hyperflow:background, "list background agents"…
local-frontend-check
Smoke-test or verify UI behaviour on the local Jarvis Registry frontend running at http://localhost/gateway. Use for manual regression checks, bug-fix verification, and end-to-end confirmation of specific flows without running the automated test suite.