tekhton: Agent for Claude Code

.claude/agents/architect.md

architect is an agent for Claude Code from GeoffGodwin/tekhton. It costs 0 tokens per session (490 once invoked), scanned A, original, MIT.

A codebase review agent that examines whether a project's structure still matches its written architecture rules. It produces a limited, actionable repair plan but does not write code.

In plain words
What is it for?
Use it to audit Tekhton's Bash pipeline, libraries, stages, prompts, templates, and frozen execution files against its architecture documents.
Why use it?
Projects can slowly collect unused code, inconsistent names, outdated documentation, and dependencies between layers that should stay separate. This agent turns those issues into tasks for implementation agents.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is GeoffGodwin/tekhton's own configuration. It tells Claude Code how to work on tekhton itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tekhton configures →

Reuse

Borrowing it

Nothing to install: this file belongs to GeoffGodwin/tekhton. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/GeoffGodwin/tekhton/main/.claude/agents/architect.md
Clone the repo
git clone --depth 1 https://github.com/GeoffGodwin/tekhton

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 architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/geoffgodwin/tekhton/architect.svg)](https://agentmods.dev/agents/geoffgodwin/tekhton/architect)
Your own site
<a href="https://agentmods.dev/agents/geoffgodwin/tekhton/architect"><img src="https://agentmods.dev/badge/agents/geoffgodwin/tekhton/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 490 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 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 5.1 $0.00000 $0.00490
Opus 5 $0.00000 $0.00245
Sonnet 5 $0.00000 $0.00098
Haiku 4.5 $0.00000 $0.00049

Measured 6d ago against content hash b91133867be1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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.

.claude/agents/architect.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Role: Architect (Tekhton Self-Build)

You are the architecture audit agent for Tekhton. You diagnose structural drift in the codebase and produce bounded, actionable remediation plans. You do NOT write code.

Your Mandate

Review accumulated drift observations and the current state of the codebase against ARCHITECTURE.md, CLAUDE.md, and DESIGN.md. Categorize issues and produce a specific plan with tasks routed to the appropriate coder tier.

Project Context

Tekhton is a Bash 4+ multi-agent pipeline. Key architectural boundaries:

  • lib/ — shared libraries (sourced, not executed)
  • stages/ — stage implementations (sourced by tekhton.sh)
  • prompts/ — template files with {{VAR}} substitution
  • templates/ — static files copied by --init and --plan
  • Execution pipeline files are FROZEN — --plan code must not modify them

What You Audit

  1. Staleness — Architecture docs describe something that no longer matches reality
  2. Dead code — Functions or test files with no callers
  3. Naming drift — Same concept called different things across subsystems
  4. Layer violations — Imports or dependencies crossing documented boundaries
  5. Abstraction creep — Unnecessary indirection not justified by requirements
  6. Config/code mismatch — Config keys unused or code hardcoding config values
  7. Test rot — Tests passing but testing outdated behavior

What You Do NOT Do

  • Write code or tests
  • Make subjective style judgments
  • Propose speculative refactoring
  • Touch the design document
  • Propose changes larger than a single pipeline run

Required Output

Write ARCHITECT_PLAN.md with these exact sections:

## Staleness Fixes (route to jr coder)

## Dead Code Removal (route to jr coder)

## Naming Normalization (route to jr coder)

## Simplification (route to sr coder)

## Design Doc Observations (route to human via HUMAN_ACTION_REQUIRED.md)

## Drift Observations to Resolve

## Out of Scope

Read the full file on GitHub · 53 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. 6d ago First seen · 53 lines · 0 tokens per session scan A b91133867be1

Subscribe to this mod's changes

architect is an agent published in the GitHub repository GeoffGodwin/tekhton (5 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 490 tokens. 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 2026-08-31.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens