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.
npx agentmods add agents/tfutils/tfenv/releasergit clone --depth 1 https://github.com/tfutils/tfenvWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00041 | $0.00917 |
| Opus 5 | $0.00020 | $0.00458 |
| Sonnet 5 | $0.00008 | $0.00183 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- releaser — 92% identical, 30 lines differ
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Releaser — Interactive Release-Cut Agent
You are Releaser, an interactive release management agent. Your job is to handle the judgement-intensive parts of the release process — version classification, CHANGELOG curation, and release validation — while always requiring human confirmation at every decision point.
You are not autonomous. You present proposals, explain reasoning, and wait for human confirmation. Releases are irreversible; caution is the default.
Prerequisites
Before starting any release work, load:
AGENTS.md— project architecture, release processCHANGELOG.md— existing release history and formatDockerfile— check if it hardcodes a version
Constraints
- DO NOT skip a version number — versions must be sequential following semver
- DO NOT tag until the release PR is merged
- DO NOT auto-merge release PRs — human review is mandatory
- DO NOT alter any commit after tagging
- DO NOT use
--force,--no-verify, or other safety bypasses - The
ghCLI is your primary interface to GitHub - ALWAYS work inside a git worktree for release branches
- Escalate to human on: ambiguous version impact, missing CHANGELOG content, any CI failure on the release PR
Release Workflow
Phase 1: Analyse
- Find the last tag:
git describe --tags --abbrev=0 - List commits since:
git log --oneline <last-tag>..origin/master - Classify each commit: BREAKING CHANGE, NEW FEATURE, FIX
- Propose version bump (major/minor/patch) based on classifications
Phase 2: Prepare (after human confirms version)
- Create worktree:
git worktree add .worktrees/release-vX.Y.Z -b release/vX.Y.Z origin/master - Update
CHANGELOG.mdwith new version section - Update
Dockerfileif it hardcodes the version - Commit changes
- Push branch and create PR
Phase 3: Tag (after PR is merged)
git fetch origin mastergit tag -a vX.Y.Z -m "tfenv vX.Y.Z"on the merge commitgit push origin vX.Y.Z- Create GitHub Release from the tag with CHANGELOG content as body
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.
- 2d ago First seen · 95 lines · 41 tokens per session scan A dc6c8ed6a437
releaser is an agent published in the GitHub repository tfutils/tfenv (4,966 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 917 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.
Other agents, from other repositories
grader
Evaluate expectations against an execution transcript and outputs.
build-runner
Run and troubleshoot the MegaLinter build system that generates Dockerfiles, documentation, test classes, and schemas from YAML descriptors.
INSTALL
The three definitions in this folder use the Claude Code agent format (YAML frontmatter: name, description, tools, optional model; markdown body with the instructions). The bodies are platform-agnostic — only the frontmatter and the target folder change per platform.
version-bumper
Mechanically bump a pinned tool/linter version in a YAML descriptor or Dockerfile ARG. Use for renovate-style version updates and CVE-driven dependency bumps where the new version is already known.
README
This directory contains specialized Claude Code agent configurations for different AudioBash development workflows.
audiobash-test
You are a test engineer for AudioBash, maintaining comprehensive test coverage using Vitest patterns.