pi-commandcode-release

Release instructions for pi-commandcode-provider, covering version changes, changelogs, package publishing, Git tags, GitHub releases, and follow-up checks.

In plain words
What is it for?
Use it to prepare and validate a release, create the required branch and tag, publish the npm package, create the GitHub release, and verify the results.
Why use it?
It makes releases traceable and reduces the risk of publishing the wrong version or changing shared repository history without approval.

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/patlux/pi-commandcode-provider/pi-commandcode-release
Any agent
npx skills add patlux/pi-commandcode-provider --skill pi-commandcode-release
Clone the repo
git clone --depth 1 https://github.com/patlux/pi-commandcode-provider

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 737 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 $0.00047 $0.00737
Opus 5 $0.00023 $0.00368
Sonnet 5 $0.00009 $0.00147
Haiku 4.5 $0.00005 $0.00074

Measured yesterday against content hash 303f6b059973, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pi-commandcode-release 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.

.agents/skills/pi-commandcode-release/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pi-commandcode-provider Release Skill

Use this skill for every pi-commandcode-provider release.

Core rule

Keep release work explicit and auditable. Do not publish, tag, push, or merge unless the user explicitly asks in the current conversation.

Required release order

Preferred order for stable releases:

  1. Create a release branch with the version/changelog changes.
  2. Open a release PR.
  3. Wait for CI to pass.
  4. Create a local annotated git tag for the release commit while the PR is still open.
  5. Publish the npm package from the release branch/commit.
  6. Create the GitHub Release from the release tag.
  7. Verify npm and the GitHub Release.
  8. Merge the release PR into main.
  9. Move/recreate the git tag on the merge commit if the project requires tags to point at main, then force-update only after explicit user approval. Prefer documenting the tag target instead of force-updating.
  10. Comment on included PRs/issues after the package and GitHub Release are live.

If branch protection or repository policy requires tags to point at main, ask before changing the order or force-updating a tag.

Version and changelog

  • Increase semver appropriately; for a patch release use npm version patch --no-git-tag-version.
  • Update CHANGELOG.md in the same PR.
  • Add a dated section for the new version.
  • Include user-facing changes and dependency/security fixes.
  • Include a Contributors subsection for every release that had external reports, PRs, testing, or issue validation.

Example changelog structure:

## 0.4.1 - 2026-06-16

- Fix provider registration for newer pi versions.
- Resolve npm audit findings.

### Contributors

- @user-a — fixed provider registration.
- @user-b — reported/validated retry behavior.

Validation

Run the checks from RELEASE.md. For this repo, at minimum:

npm test
npm run typecheck
npm run format:check
npm audit --audit-level=moderate
npm pack --dry-run
git diff --check

If local pi auth makes test:pi-local use the wrong provider state, rerun the suite with a harmless mock Command Code API key in the environment instead of real auth.

Read the full file on GitHub · 103 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. yesterday First seen · 103 lines · 47 tokens per session scan A 303f6b059973

Subscribe to this mod's changes

pi-commandcode-release is a skill published in the GitHub repository patlux/pi-commandcode-provider (131 stars, last pushed 6d ago), licensed MIT. It adds 47 tokens to every session and 737 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 2026-08-30.

Related

Other skills, from other repositories

surf

Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.

w-winter/dot314 · 60 tokens

prose-review

Review prose written for others -- user-facing docs, prompts for other LLMs, inline comments, docstrings, and other-facing messages -- for local jargon leakage, orphaned references, missing grounding, and audience or genre misfit.

w-winter/dot314 · 50 tokens

text-search

Search indexed text corpora with qmd. For indexed content, prefer qmd over grep.

w-winter/dot314 · 22 tokens

repoprompt-tool-guidance-refresh

Refresh RepoPrompt tool guidance when the CLI/MCP surface changes. Tracks RepoPrompt CE (rpce-cli, the maintained target) across versions, and can diff the frozen Classic CLI (rp-cli) against CE. Uses /.pi/agent/skills/repoprompt-tool-guidance-refresh/scripts/track-rp-version.sh to capture/diff --help and -l (tool…

w-winter/dot314 · 115 tokens

xcodebuildmcp

Build/test Xcode projects via the XcodeBuildMCP MCP server using a local CLI wrapper for pi (no MCP support). Use when the user mentions Xcode, xcodebuild, iOS builds/tests, or XcodeBuildMCP.

w-winter/dot314 · 56 tokens

agent-browser

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

w-winter/dot314 · 51 tokens