ga: Skill for Claude Code

.claude/skills/chatbot-iterate/SKILL.md

Chatbot Iterate is a skill for Claude Code from GuitarAlchemist/ga. It costs 74 tokens per session (4,248 once invoked), scanned A, original, MIT.

A guided development loop for chatbot work. It selects an item from BACKLOG.md and takes it through feature definition, planning, implementation, review, and pull-request preparation.

In plain words
What is it for?
Use it to work through chatbot backlog items one at a time, with required tribunal and multi-model review for specified parts of the codebase.
Why use it?
It gives chatbot changes a repeatable process and identifies extra review requirements before merging changes to sensitive chatbot, tool, parser, or dependency-injection code.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

This is GuitarAlchemist/ga's own configuration. It tells Claude Code how to work on ga 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 ga configures →

Reuse

Borrowing it

Nothing to install: this file belongs to GuitarAlchemist/ga. 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/GuitarAlchemist/ga/main/.claude/skills/chatbot-iterate/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/GuitarAlchemist/ga

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 Chatbot Iterate

README.md
[![agentmods](https://agentmods.dev/badge/skills/guitaralchemist/ga/chatbot-iterate.svg)](https://agentmods.dev/skills/guitaralchemist/ga/chatbot-iterate)
Your own site
<a href="https://agentmods.dev/skills/guitaralchemist/ga/chatbot-iterate"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/chatbot-iterate.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,248 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 $0.00074 $0.04248
Opus 5 $0.00037 $0.02124
Sonnet 5 $0.00015 $0.00850
Haiku 4.5 $0.00007 $0.00425

Measured 7d ago against content hash 794103a72a82, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Chatbot Iterate 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 7d 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/skills/chatbot-iterate/SKILL.md · 427 lines

How it starts

The opening of the file, as written. The whole thing — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/chatbot-iterate

Glue skill that ties the existing pieces (/feature, /work, /octo:review, the Demerzel QA tribunal, /learnings, /ce-compound) into a single chatbot-scoped iteration loop. Emits a clear gate plan up front so the human knows what review the change will need before merging.

This is the Level 2 automation in our chatbot-development ladder (per the discussion in docs/automation/chatbot-loop.md): assistant drives end-to-end on one item, human reviews and merges. Not Level 3 (auto-merge on multi-LLM green) or Level 4 (failure-fed dark factory).

When to Run

  • "Pick up the next chatbot thing" — moving down the chatbot backlog systematically.
  • After shipping a chatbot feature, when the next item is queued and the assistant should keep the cadence.
  • Not for general feature work — use /feature directly. This skill exists to enforce the chatbot-specific gates.

Iron Law

ANY PR touching the following paths REQUIRES Demerzel tribunal verdict
+ multi-LLM review (octopus or codex) BEFORE merge:

  Common/GA.Business.ML/Agents/**
  Common/GA.Business.ML/**/Mcp/**
  Apps/ga-server/GaApi/Mcp/**
  Common/GA.Business.DSL/**
  **/IChatClientFactory*
  **/AddGuitarAlchemistAi*

The "feedback_multi_llm_review_pays_off" memory documents that
multi-LLM review caught 9 real bugs in PR #151 alone that local
tests missed. This gate is load-bearing, not bureaucratic.

NEVER mark a PR ready-for-merge on a chatbot path until both gates
have been satisfied.

Process

Step 0: Killswitch + governance-directives check

Before doing ANYTHING, check the two halt signals.

A. Local killswitch (operator-owned):

if (Test-Path state/.loop-halted) {
    Write-Host "Loop halted — sentinel present. Aborting." -ForegroundColor Red
    Get-Content state/.loop-halted
    exit 0
}

To resume:

pwsh Scripts/loop-killswitch.ps1 -Reset

Status check (read-only):

pwsh Scripts/loop-killswitch.ps1 -Status

Read the full file on GitHub · 427 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. 7d ago First seen · 427 lines · 74 tokens per session scan A 794103a72a82

Subscribe to this mod's changes

Chatbot Iterate is a skill published in the GitHub repository GuitarAlchemist/ga (2 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 4,248 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens