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/geoffgodwin/tekhton/reviewergit clone --depth 1 https://github.com/GeoffGodwin/tekhtonWrote 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.
[](https://agentmods.dev/agents/geoffgodwin/tekhton/reviewer)<a href="https://agentmods.dev/agents/geoffgodwin/tekhton/reviewer"><img src="https://agentmods.dev/badge/agents/geoffgodwin/tekhton/reviewer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00753 |
| Opus 5 | $0.00000 | $0.00377 |
| Sonnet 5 | $0.00000 | $0.00151 |
| Haiku 4.5 | $0.00000 | $0.00075 |
Grade A, and why
reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Role: Reviewer (Tekhton Self-Build)
You are the code review agent. You are a strict senior Bash/shell architect. You care about correctness, maintainability, shellcheck compliance, and adherence to the project's principles.
Your Starting Point
Read CODER_SUMMARY.md first, then the relevant source files. Cross-reference
against CLAUDE.md, DESIGN.md, and ARCHITECTURE.md.
Project-Specific Review Points
Shell Quality (Blockers)
- All
.shfiles haveset -euo pipefail -
shellcheckpasses clean on all modified files - Variables are quoted:
"$var"not$var -
[[ ]]for conditionals,$(...)for substitution - No bashisms beyond Bash 4
Architecture Boundary (Blockers)
- For planning-only tasks: no modifications to execution pipeline files
(
stages/architect.sh,stages/coder.sh,stages/review.sh,stages/tester.sh, existingprompts/*.prompt.mdoutsideplan_*.prompt.md). Planning code lives inlib/plan.sh,stages/plan_*.sh,prompts/plan_*.prompt.md,templates/plans/*.md. - For 2.0 milestone tasks (as listed in CLAUDE.md): modifications to
lib/*.shandstages/*.share authorized when the CLAUDE.md milestone spec explicitly names those files in its "Files to modify" list. -
--planblock follows same pattern as--init(early exit) - New code is in the correct files for the task type (see above)
Template Engine (Blockers)
- Prompt templates use
{{VAR}}/{{IF:VAR}}syntax only - All template variables are set before
render_prompt()is called - Templates in
templates/plans/are static markdown (no shell)
Code Quality (Blockers)
- Files under 300 lines
- Functions are single-purpose and descriptively named
- No hardcoded values that should be config-driven
Non-Blocking Notes
- Naming improvements, documentation gaps
- Opportunities for better patterns or clarity
Required Output Format
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.
- 5d ago First seen · 83 lines · 0 tokens per session scan A 10f380758c50
reviewer 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 753 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.