ship-feature

A release-completion workflow for a finished feature: it checks changes and tests, updates project roadmap and release notes, commits the work, and pushes it to the remote repository.

In plain words
What is it for?
Running the test suite, adding missing Vitest tests, moving a roadmap item to shipped, writing release notes, committing changes, and pushing to origin.
Why use it?
It provides a checklist for confirming that new logic is tested and that project records and version-control history reflect the completed feature.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/vicmaster/coide/ship-feature
Any agent
npx skills add vicmaster/coide --skill ship-feature
Clone the repo
git clone --depth 1 https://github.com/vicmaster/coide

Made for: Claude Code, Codex.

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 668 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.00668
Opus 5 $0.00015 $0.00334
Sonnet 5 $0.00006 $0.00134
Haiku 4.5 $0.00003 $0.00067

Measured 2d ago against content hash 67d47be6dffc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ship-feature 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.

.claude/skills/ship-feature/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship Feature

Wrap up a completed feature: ensure tests exist and pass, commit all changes, move it from VISION.md's roadmap into SHIPPED.md, add to release notes, and push.

Instructions

  1. Run git status and git diff to see all staged and unstaged changes
  2. Verify tests exist for the feature:
    • Look at the changed/added files and identify any new store actions, utility functions, or event parsing logic
    • Check if corresponding test files already exist under src/__tests__/
    • If tests are missing for new logic, write Vitest tests before proceeding:
      • Store actions → src/__tests__/store/
      • Utility functions → src/__tests__/utils/
      • Follow the existing test patterns (see sessions.test.ts, diff.test.ts, mcpParsing.test.ts for examples)
    • Pure UI components without logic don't require tests, but any extracted logic they use does
  3. Run the full test suite with npx vitest run
    • If any test fails, fix the issue and re-run until all tests pass
    • Do NOT proceed to commit if tests are failing
  4. Read VISION.md and find the unchecked item (- [ ]) under ## Roadmap that best matches: "$ARGUMENTS"
    • If no match is found, list the unchecked items and ask which one (or skip — polish/bug fixes don't always map to a roadmap item)
  5. Move the matched item to SHIPPED.md:
    • Remove the - [ ] line from VISION.md's ## Roadmap section
    • Append the item (without the [ ] checkbox, just - Feature name — description) to the appropriate section in SHIPPED.md (e.g. ## Core Roadmap (shipped) or ## Copycat — Features parity with Claude Code CLI (shipped)); if no section fits, add to a ## Misc (shipped) section, creating it if absent
    • If step 4 was skipped (no roadmap match), do NOT touch VISION.md or SHIPPED.md in this step
  6. Update release notes in src/renderer/src/data/releaseNotes.ts:
    • Always append a one-line description to the first entry's notes array (regardless of what version it shows — the release script renames it on release)
    • Keep note descriptions concise (under 80 chars), user-facing language (not implementation details)
  7. Stage all relevant changed files (including the VISION.md/SHIPPED.md updates, release notes update, and any new test files)
  8. Write a commit message that describes the feature work done (based on the actual code changes), NOT just "mark as done"
  9. Commit and push to origin

Read the full file on GitHub · 38 lines

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. 2d ago First seen · 38 lines · 31 tokens per session scan A 67d47be6dffc

Subscribe to this mod's changes

ship-feature is a skill published in the GitHub repository vicmaster/coide (10 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 668 once invoked, about $0.0002 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.