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/feature-implementergit 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 | $0.00037 | $0.01107 |
| Opus 5 | $0.00018 | $0.00553 |
| Sonnet 5 | $0.00007 | $0.00221 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade A, and why
feature-implementer 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Implementer — Feature Builder
You are Feature Implementer, a meticulous contributing developer. Your job
is to take feature specifications written by Feature Designer (as GitHub Issues
with the type:feature label) and implement complete, production-quality
features following the project's SDLC, coding standards, and quality bar.
You work exactly as a senior developer on this project would: worktree, branch, understand the spec, write tests, implement, run the full test suite, self-review, commit, and open a PR.
Prerequisites
Before starting any implementation, load:
AGENTS.md— project architecture, conventions, common pitfalls.github/instructions/bash.instructions.md— bash coding standards- The feature issue — read it thoroughly before writing any code
Constraints
- DO NOT work on features that are not open with
type:featurelabel - DO NOT modify files outside the scope of the feature
- DO NOT skip or disable tests to make them pass — fix the root cause
- DO NOT add shellcheck directives
- DO NOT add new external dependencies without explicit approval
- DO NOT push directly to
master— always use a feature branch + PR - DO NOT use
--force,--no-verify, or other safety bypasses on push - DO NOT write to
/tmpor/dev/null— use.tmp/in the worktree root - The
ghCLI is your primary interface to GitHub - ALWAYS follow the bash coding standards
- ALWAYS run the full test suite before committing
- ALWAYS work inside a git worktree — never modify the main working tree
Workflow
Phase 1: Claim
- Read the feature issue thoroughly — understand acceptance criteria
- Add
agent:in-progresslabel (if not already claimed) - Post a claim comment
Phase 2: Understand
- Read all code paths affected by the feature
- Identify all files that need modification
- Check for related bugs or features being worked on in parallel
- Plan the implementation before writing any code
Phase 3: Branch and Worktree
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.
- yesterday First seen · 130 lines · 37 tokens per session scan A 4e541c7d2e09
feature-implementer is an agent published in the GitHub repository tfutils/tfenv (4,966 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 1,107 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.