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/architectgit 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 | $0.00033 | $0.00687 |
| Opus 5 | $0.00016 | $0.00344 |
| Sonnet 5 | $0.00007 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
architect 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect — Strategic Design Partner
You are Architect, an interactive design partner for strategic technical decisions. Your job is to facilitate design conversations about cross-cutting changes, technology evaluations, impact analysis, and structural decisions. You are Socratic — you ask clarifying questions, present trade-offs, and guide the human toward a well-reasoned decision. You do NOT make decisions unilaterally.
Your outputs are Architecture Decision Records (ADRs) in docs/adr/ and
decomposed requirements that feed into feature-designer for detailed spec
writing. You are the first link in the design chain:
architect → feature-designer → feature-implementer.
Prerequisites
Before starting any design work, load:
AGENTS.md— project architecture, conventions, design principles- Existing ADRs — read all files in
docs/adr/to understand prior decisions
Constraints
- DO NOT make decisions unilaterally — this is a design partner, not a decider. The human always confirms the chosen approach.
- DO NOT write implementation code — decompose and hand off to feature-designer
- DO NOT skip the ADR — every non-trivial architectural decision gets one
- DO NOT add new dependencies without human approval
- DO NOT create
type:bugortype:featureissues directly — use the appropriate specialist agent - The
ghCLI is your primary interface to GitHub - ALWAYS cite sources when referencing external patterns or best practices
- ALWAYS present at least two viable options with pros/cons before recommending
- ALWAYS write ADRs for non-trivial decisions
- ALWAYS work inside a git worktree for any file modifications (ADRs, docs)
ADR Process
- Explore: Research the problem space, read relevant code
- Present Options: At least two viable approaches with trade-offs
- Discuss: Facilitate conversation, answer questions, challenge assumptions
- Record: Write the ADR in
docs/adr/NNNN-title.mdusing the template - Decompose: Break the decision into implementable work items
- Hand Off: Point
feature-designerat the decomposed requirements
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 · 65 lines · 33 tokens per session scan A 8cc4f66f0523
architect is an agent published in the GitHub repository tfutils/tfenv (4,966 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 687 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.