release

release is a skill for Claude Code, Codex from iksnerd/adb-mcp. It costs 136 tokens per session (1,995 once invoked), scanned A, original, MIT.

A release checklist for adb-mcp, a project that provides tools through the Model Context Protocol (MCP). It covers reviewing changes, testing tools, updating versions, writing release notes, and publishing a tagged release.

In plain words
What is it for?
It helps prepare, verify, document, tag, push, and confirm adb-mcp releases.
Why use it?
It reduces the risk of publishing a broken release when pushing a version tag automatically builds and publishes the project.

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/iksnerd/adb-mcp/release
Any agent
npx skills add iksnerd/adb-mcp --skill release
Clone the repo
git clone --depth 1 https://github.com/iksnerd/adb-mcp

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/iksnerd/adb-mcp/release.svg)](https://agentmods.dev/skills/iksnerd/adb-mcp/release)
Your own site
<a href="https://agentmods.dev/skills/iksnerd/adb-mcp/release"><img src="https://agentmods.dev/badge/skills/iksnerd/adb-mcp/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,995 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00136 $0.01995
Opus 5 $0.00068 $0.00997
Sonnet 5 $0.00027 $0.00399
Haiku 4.5 $0.00014 $0.00199

Measured 5d ago against content hash 4cb4d20487d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

release 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (mcp_drive.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

curl -fsS "https://registry.modelcontextprotocol.io/v0/servers?search=io.github.iksnerd/adb-mcp"
.claude/skills/release/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cutting an adb-mcp release

Everything runs off one tag push. .github/workflows/release.yml triggers only on v* — there is no push/PR CI — so the tag is simultaneously the build, the test run, the GitHub Release, and the MCP registry publish. A bad tag is therefore public before you find out.

The rule that follows from that: replicate the gate locally before tagging. Re-tagging is the only fix, and the registry has already seen the old version.

Order of operations

  1. Review what landed since the last tag.
  2. Verify the new tools live (see below — this is not optional here).
  3. Fix what the review found. Do not tag around a known bug in unreleased code.
  4. Bump the four version files + write the CHANGELOG section.
  5. make docs to sync every derived count.
  6. Run the gate locally.
  7. Tag, push, watch, confirm.

1. Review

git log --oneline "$(git describe --tags --abbrev=0)"..HEAD
git status --short          # uncommitted feature work is common here
git diff

Working-tree changes matter as much as commits: features often sit uncommitted with their docs already written. Read docs/BACKLOG.md — entries are updated to [x] with a "Verified…" note when something ships, and that note is a claim you are about to put your name on.

2. Verify live, don't reason from the diff

A passing go test says the parser works. It does not say the tool works. Drive the freshly built binary over real stdio JSON-RPC:

go build -o "$SCRATCH/adb-mcp" ./cmd/adb-mcp
python3 .claude/skills/release/mcp_drive.py "$SCRATCH/adb-mcp" \
  'session_set_defaults|{"project_dir":"/path/to/project"}' \
  'get_coverage_report|{}'

Exercise the error paths too (missing arg, not-found, ambiguous input), and hand-check the numbers against the source rather than accepting a plausible percentage.

Test the shape the feature is actually for. A Gradle tool verified only on a single-module project is barely verified: most Android projects are multi-module, and that is where jacocoTestReport fans out across modules and per-tool assumptions break. The v0.22.0 coverage bug — reporting one module and silently dropping the rest — passed every unit test and a single-module live run.

Read the full file on GitHub · 164 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. 5d ago First seen · 164 lines · 136 tokens per session scan A 4cb4d20487d2

Subscribe to this mod's changes

release is a skill published in the GitHub repository iksnerd/adb-mcp (3 stars, last pushed 10d ago), licensed MIT. It adds 136 tokens to every session and 1,995 once invoked, about $0.0007 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.