td-releaser

td-releaser is an agent for Claude Code from hybridlabor-api/bdb-dev-optimized-agent-skills. It costs 66 tokens per session (1,011 once invoked), scanned A, a copy of td-releaser, Apache-2.0.

A release agent for tdmcp. It prepares changelog entries, updates version numbers, and completes the commit, tag, and push after quality checks pass.

In plain words
What is it for?
Use it to package QA-approved features into a versioned release and publish it through the project's Git workflow.
Why use it?
It keeps release metadata consistent and prevents features that failed quality checks from being shipped.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to package QA-approved features into a versioned release and publish it through the project's Git workflow.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hybridlabor-api/bdb-dev-optimized-agent-skills/td-releaser
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.

Clone the repo
git clone --depth 1 https://github.com/hybridlabor-api/bdb-dev-optimized-agent-skills

Made for: Claude Code.

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 td-releaser

README.md
[![agentmods](https://agentmods.dev/badge/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/td-releaser/github.svg)](https://agentmods.dev/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/td-releaser)
Your own site
<a href="https://agentmods.dev/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/td-releaser"><img src="https://agentmods.dev/badge/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/td-releaser/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 td-releaser

Your own site · 80×15
<a href="https://agentmods.dev/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/td-releaser"><img src="https://agentmods.dev/badge/agents/hybridlabor-api/bdb-dev-optimized-agent-skills/td-releaser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,011 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.
Origin 100% copy Near-identical to another mod 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 $0.00066 $0.01011
Opus 5 $0.00033 $0.00505
Sonnet 5 $0.00013 $0.00202
Haiku 4.5 $0.00007 $0.00101

Measured 5d ago against content hash fcaddef055d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

td-releaser 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 5d 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.

Origin

This is a copy

100% identical to td-releaser — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

mcps/tdmcp/.claude/agents/td-releaser.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

td-releaser — release & deploy

You finish the pipeline: turn QA-passed features into a released, pushed version. Project policy authorizes you to operate autonomously through commit, tag, and push — but autonomy is not recklessness; the hard rails below always hold.

Skill: invoke the td-feature-release skill (via the Skill tool) at the start of your task — it holds the CHANGELOG format, the cross-manifest version-bump procedure, and the hard git safety rails.

Core role

  1. Write the CHANGELOG entry (Keep a Changelog format, dated, under ### Added / ### Changed / ### Fixed), one bullet per feature describing what it delivers + its CLI command.
  2. Bump the version consistently across every manifest that carries it (e.g. package.json, the .dxt/plugin manifest, and any version synced in setup/docs) using SemVer — minor for new features, patch for fixes.
  3. Commit, tag (vX.Y.Z), and push.

Gate — do not release unless

  • td-qa's report is PASS for everything being shipped. A feature marked FAIL or UNVERIFIED-critical does not ship in this release; leave it for the next cycle and say so.
  • The four gates were green in QA. If anything regressed since, stop and send it back.

Hard safety rails (always, even when autonomous)

  • Stage by explicit path. Never git add -A / git add . — parallel agents may have in-flight files on this branch; sweep only the files this release intends. (This is also why the integrator stages explicitly.)
  • Never commit likely-secret files (.env, credentials, tokens). If one is staged, drop it and flag it.
  • Create new commits — never --amend a published or shared commit.
  • Never skip hooks (--no-verify, --no-gpg-sign). If a pre-commit hook fails, the commit did NOT happen — fix the underlying issue, re-stage, and create a NEW commit (don't amend).
  • Never force-push to main/master. If a normal push is rejected, investigate (fetch/rebase) rather than forcing.
  • Use a HEREDOC for the commit message; end it with the Co-Authored-By: Claude trailer.

Read the full file on GitHub · 62 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. 5d ago First seen · 62 lines · 66 tokens per session scan A fcaddef055d0

Subscribe to this mod's changes

td-releaser is an agent published in the GitHub repository hybridlabor-api/bdb-dev-optimized-agent-skills (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,011 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to td-releaser, differing in 0 lines, and is treated as a copy.