tangerine: Skill for Claude Code

.agents/skills/release-semver/SKILL.md

release-semver is a skill for Claude Code, Codex from dinhtungdu/tangerine. It costs 51 tokens per session (2,215 once invoked), scanned A, original, MIT.

A release workflow for publishing a new semantic version of a project or package. Semantic versioning uses version numbers such as 1.2.3 to show the size of a change.

In plain words
What is it for?
Use it when making patch, minor, major, or prerelease releases from Tangerine projects, provided the required repository access is available.
Why use it?
It coordinates version updates, review, merging, publishing, and tagging while following repository protection rules.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is dinhtungdu/tangerine's own configuration. It tells Claude Code and Codex how to work on tangerine itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tangerine configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dinhtungdu/tangerine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dinhtungdu/tangerine/main/.agents/skills/release-semver/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/dinhtungdu/tangerine

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 release-semver

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/dinhtungdu/tangerine/release-semver"><img src="https://agentmods.dev/badge/skills/dinhtungdu/tangerine/release-semver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,215 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00051 $0.02215
Opus 5 $0.00026 $0.01107
Sonnet 5 $0.00010 $0.00443
Haiku 4.5 $0.00005 $0.00221

Measured 9d ago against content hash 8c8ae1077539, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

release-semver scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

compatibility: "Requires Tangerine task API, git, gh, jq, curl, Bun, network access. Package publish credentials only needed for repos without a GitHub release-triggered publish workflow."
.agents/skills/release-semver/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Semver

Use when user asks to release a new semantic version of a project/package.

Goal: coordinator does release orchestration only. Worker edits version files. Coordinator watches PR, merges it without human handoff, pulls main, publishes release.

Preconditions

  • User gave target version (1.2.3) or bump kind (patch, minor, major, prerelease). If missing, ask once.
  • Run from project root/main clone, ideally as a runner task.
  • gh authenticated with permission to merge and publish releases.
  • Never use bypass flags: no --admin, no --force, no --no-verify.
  • Only use gh pr merge when current user explicitly requested unattended merge/release in this task, or repo owner matches gh api user --jq .login.

1. Resolve Tangerine context

API=http://localhost:${TANGERINE_PORT:-3456}
AUTH_SESSION=$(curl -s "$API/api/auth/session")
echo "$AUTH_SESSION" | jq '{enabled, authenticated}'
AUTH_ENABLED=$(echo "$AUTH_SESSION" | jq -r '.enabled // false')
if [ "$AUTH_ENABLED" = "true" ] && [ -z "$TANGERINE_AUTH_TOKEN" ]; then
  echo "Tangerine auth enabled but TANGERINE_AUTH_TOKEN missing" >&2
  exit 1
fi

TASK_JSON=$(curl -s -H "Authorization: Bearer $TANGERINE_AUTH_TOKEN" "$API/api/tasks/$TANGERINE_TASK_ID")
PROJECT_ID=$(echo "$TASK_JSON" | jq -r '.projectId')
DEFAULT_BRANCH=$(curl -s -H "Authorization: Bearer $TANGERINE_AUTH_TOKEN" "$API/api/projects/$PROJECT_ID" | jq -r '.defaultBranch // "main"')

2. Compute next version

If exact version provided, use it. If bump kind provided and repo has package.json:

CURRENT_VERSION=$(jq -r '.version' package.json)
# Use node semver when available; otherwise compute patch/minor/major manually.

Before continuing:

git fetch origin "$DEFAULT_BRANCH"
git checkout "$DEFAULT_BRANCH"
git pull --ff-only origin "$DEFAULT_BRANCH"
test -z "$(git status --short)" || { git status --short; echo "Working tree dirty" >&2; exit 1; }

3. Spawn worker to bump version

Read the full file on GitHub · 241 lines

Files

What ships with it

1 file 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. 9d ago First seen · 241 lines · 51 tokens per session scan A 8c8ae1077539

Subscribe to this mod's changes

release-semver is a skill published in the GitHub repository dinhtungdu/tangerine (5 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 2,215 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.