spectre-ship

spectre-ship is a skill for Claude Code, Codex from joenandez/spectre. It costs 70 tokens per session (1,675 once invoked), scanned A, original, MIT.

A workflow for turning finished branch work into a pull request, a review request for code changes. It cleans and rebases the branch, observes the full test suite, handles failures, and opens the pull request.

In plain words
What is it for?
Use it when finished branch work needs to be prepared, checked, and opened as a pull request.
Why use it?
It provides a defined handoff path for completed work and records test results and any repairs or routing decisions. It is intended for reviewer-ready changes rather than implementation work.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present.

Good fit Use it when finished branch work needs to be prepared, checked, and opened as a pull request.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joenandez/spectre/spectre-ship
Install

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.

Any agent
npx skills add joenandez/spectre --skill spectre-ship
Clone the repo
git clone --depth 1 https://github.com/joenandez/spectre

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for spectre-ship

README.md
[![agentmods](https://agentmods.dev/badge/skills/joenandez/spectre/spectre-ship/github.svg)](https://agentmods.dev/skills/joenandez/spectre/spectre-ship)
Your own site
<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-ship"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-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.

agentmods 80×15 button for spectre-ship

Your own site · 80×15
<a href="https://agentmods.dev/skills/joenandez/spectre/spectre-ship"><img src="https://agentmods.dev/badge/skills/joenandez/spectre/spectre-ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,675 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.01675
Opus 5.5 $0.00028 $0.00670
Sonnet 5.5 $0.00014 $0.00335
Haiku 4.5 $0.00007 $0.00168

Measured 1mo ago against content hash 3719023e9f83, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spectre-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 1mo 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.

plugins/spectre-codex/skills/spectre-ship/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ship

Own cleanup, rebase, advisory suite, and draft PR.

Inputs

  • $ARGUMENTS: optional feature root/artifact, target (default origin/main), feedback focus, or --draft; live branch/tree/remotes/PR state.

Feature root

  • Reuse a managed FEATURE_ROOT only when explicit/current-thread evidence ties it to this work (physical directory wins; never branch/recency/lifecycle/scans); distinct work ignores ambient roots. Otherwise, including on collision, standalone MUST first load and follow Skill(spectre-feature-root) through DONE; orchestrated calls escalate. Keep writes beneath it and pass it unchanged.

Proof independence

Proof is optional: do not inspect, infer, invoke, or gate on it. Only authority/publication-safety impasses prevent PR creation.

Outputs + DONE

  • Return PR URL, commits, rebase/tested SHA, verification/repairs, CI: pending, measurement, and PR_OPENED status PASS|REPAIRED|PRE_EXISTING_FAILURES|INDETERMINATE|KNOWN_FAILURES_REMAIN.

DONE when: Prune analysts/Test testers finish their gates, then Sweep, rebase, one full suite, repair/routing, measurement relay/degradation, and PR URL. Non-green verification never prevents DONE.

Method / guardrails

  1. Resolve once. Confirm branch/target/set; reject main/master. Read the exact branch; never derive work identity from branch, recency, or ambient roots — selection binds to the frozen post-rebase candidate. FEATURE_ROOT is artifact-only. Reuse unambiguous ancestral CLEANED_THROUGH_SHA. Invoke node "${PLUGIN_ROOT}/hooks/scripts/workflow-cli.mjs" measure start --label Ship; below, measure means node "${PLUGIN_ROOT}/hooks/scripts/workflow-cli.mjs" measure.
  2. Parallel cleanup boundary. Classify P0-P3; invoke measure start for Prune/Test. Load ${PLUGIN_ROOT}/skills/spectre-ship/references/prune.md and ${PLUGIN_ROOT}/skills/spectre-ship/references/test.md with the set/risk/FEATURE_ROOT/--orchestrated. Skill loading imports instructions, not phase delegation: the primary owns both contracts and makes one parallel dispatch of leaf @spectre_analyst/@spectre_tester batches; no phase child spawns agents. Neither stages/commits. Invoke measure finish after all batches, attaching a child identity only when singular; relay compact paths/checks and repair/route cross-boundary needs unless NEEDS_AUTHORITY.
  3. Sweep. Start measure start --label "Sweep"; load ${PLUGIN_ROOT}/skills/spectre-ship/references/sweep.md with --orchestrated, unchanged set, and both results. It alone integrates stale/uncovered checks, repairs attributable failures, and commits; invoke measure finish for the Sweep snapshot.
  4. Rebase. Start measure start --label "Rebase"; load ${PLUGIN_ROOT}/skills/spectre-ship/references/rebase.md with target, --orchestrated --verification-owner parent; retain backup summary. No checks; invoke measure finish for the Rebase snapshot.
  5. Observe one full suite after rebase. At FULL_SUITE_SHA, derive and freeze candidate {repository, base, head, diff} as EXPECTED_BASE_SHA/EXPECTED_HEAD_SHA/EXPECTED_DIFF_SHA256. Before the first PR side effect, select against that frozen tuple with knowledge-cli.mjs work membership --branch <exact-branch> --candidate <tuple-json>; freeze its selected work-ID set and report excluded/ambiguous without substituting recency. Still before Create PR, invoke Skill(spectre-work-record) per selected record: finalize a complete one with execution.state finalized and remainingWork exactly None.; refresh a blocked/incomplete one truthfully and never finalize it. No PR, CI, review, or readiness value enters remainingWork. Then invoke measure start --label "Full suite" and measure start --label "Create PR". In parallel run the full-suite lane and Skill(spectre-create_pr) pending with target, --orchestrated --pr-phase pending, the frozen set, and the tuple; it returns a draft with local verification RUNNING. At each end invoke measure finish with child identity when available. No duplicate suites or raw child output.
    • Attribute failures branch-caused|unrelated|indeterminate, preferring target-SHA CI and otherwise reproducing only the failing check at target.
    • Repair branch-caused families; rerun only failing/affected checks, never the full suite. Route unrelated/indeterminate findings; record repaired HEAD and CI: pending.
    • Verification is evidence, never a stop condition.
  6. Create PR and measure. After suite call Skill(spectre-create_pr) with target, --orchestrated --pr-phase final-update, URL/body, the same frozen set, refreshed tuple, and FINAL_VERIFICATION_SUMMARY; change Testing only. Refresh claims after repairs; on PR_CANDIDATE_STALE, refresh and retry. Once PR identity exists, re-run work membership against the final tuple after any repair; a record it no longer proves is reported, not associated. Annotate the still-selected set through one work associate --work-id <id> … --pull-request-id <id> --candidate <final-json> --pull-request <json>, replaying retry.expectedRevisions via --expected-revisions until associated/noop and reporting partial remaining. Association annotates only: it never confers finality, PR state is draft-open, never merged, and a later Execute run on this branch keeps its own record and joins this same PR only when the updated candidate proves membership. Ambiguity or capture failure returns recovery input but does not block PR. Run measure summary --rows … --outer-snapshot … --persist --project-dir … --feature-root "$FEATURE_ROOT" --base-sha "$EXPECTED_BASE_SHA" --head-sha "$EXPECTED_HEAD_SHA" --diff-sha256 "$EXPECTED_DIFF_SHA256"; relay table, persistence status, and history path. Persistence degradation never blocks PR completion; never inspect transcripts, track clocks, or calculate. Unattributed Prune/Test and Full suite/Create PR use one exact parallel-group total; unavailable measurement never blocks Ship.

Read the full file on GitHub · 59 lines

Files

What ships with it

5 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.

Changes

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.

  1. 1mo ago Changed 3719023e9f83
  2. 1mo ago Changed 53f0d0966311
  3. 1mo ago Changed · -1 lines 44b6d77d8132
  4. 1mo ago Changed · +6 lines 748a9363761e
  5. 2mo ago Changed · +1 lines · -1 tokens per session e5710eb627cd
  6. 2mo ago First seen · 53 lines · 71 tokens per session scan A c9d31ffda9bc

Subscribe to this mod's changes

spectre-ship is a skill published in the GitHub repository joenandez/spectre (164 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,675 once invoked, about $0.0003 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 2026-08-30.

Related

spectre-ship compared with skills from other repositories

spectre-ship next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
spectre-shipjoenandez/spectreSkill1641mo agoMITA70Claude Code, Codex
merge-batchdiegosouzapw/OmniRouteSkill83k6d agoMITA46Claude Code
prowler-commitprowler-cloud/prowlerSkill15kyesterdayApache-2.0A44Claude Code, Codex
gh-auth-isolationgithub/gh-awSkill5.6kyesterdayMITA20Claude Code, Codex
github-skillzeenie-ai/OpenCompanySkill1.1kyesterdayMITA51Claude Code
comet-githubrpamis/cometSkill3.3kyesterdayMITA72Claude Code, Codex
release-helperSahir619/fable-methodSkill2.3k1mo agoMITA43Claude Code