controller

controller is a skill for Claude Code from quay/ai-helpers. It costs 41 tokens per session (1,586 once invoked), scanned A, original, MIT.

A staged controller for fixing software bugs. It moves through assessment, reproduction, diagnosis, coding, testing, review, and documentation, using confidence reports to decide whether to continue or ask the user.

In plain words
What is it for?
Use it to investigate reported bugs, confirm their cause, implement a fix, run regression tests, review the changes, and prepare release notes or other documentation.
Why use it?
It removes the need to coordinate each bug-fixing step manually and provides a point to escalate when the evidence is uncertain.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is Bash(bash .claude/scripts/session-setup.sh).

Good fit Use it to investigate reported bugs, confirm their cause, implement a fix, run regression tests, review the changes, and prepare release notes or other documentation.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/quay/ai-helpers
agentmods
npx agentmods add skills/quay/ai-helpers/controller

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 controller

README.md
[![agentmods](https://agentmods.dev/badge/skills/quay/ai-helpers/controller.svg)](https://agentmods.dev/skills/quay/ai-helpers/controller)
Your own site
<a href="https://agentmods.dev/skills/quay/ai-helpers/controller"><img src="https://agentmods.dev/badge/skills/quay/ai-helpers/controller.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,586 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00041 $0.01586
Opus 5 $0.00020 $0.00793
Sonnet 5 $0.00008 $0.00317
Haiku 4.5 $0.00004 $0.00159

Measured 2d ago against content hash 0c01e562d0a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

controller scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Bash(curl *)
workflows/quay-bugfix/.claude/skills/controller/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quay Bugfix Controller

You manage a 9-phase bug-fix workflow with confidence-based gating. After each phase, read the confidence assessment from the phase artifact and use it to decide whether to advance, comment, or escalate.

Session Bootstrap

On first run, ensure Lola plugins are installed:

bash .claude/scripts/session-setup.sh

Phases

  1. Assess — the assess skill Read the bug report, summarize understanding, identify gaps, propose a plan.

  2. Reproduce — the reproduce skill Confirm the bug exists by reproducing it in a controlled environment.

  3. Diagnose — the diagnose skill Trace the root cause through code analysis, git history, and hypothesis testing.

  4. Fix — the /dev:code skill (from dev plugin) Read the root cause analysis, create a feature branch, then implement the minimal fix using /dev:code. Write implementation notes afterward.

  5. Test — the test skill Write regression tests, run the full suite, and verify the fix holds.

  6. Review — the review skill Critically evaluate the fix and tests — look for gaps, regressions, and missed edge cases.

  7. Document — the document skill Create release notes, changelog entries, JIRA updates, and PR description.

  8. PR — the /dev:pr skill (from dev plugin), then /dev:poll Create a pull request using /dev:pr, then start CI polling with /dev:poll <PR#>.

  9. Summary — the summary skill Scan all artifacts and present a synthesized summary.

Confidence-Based Gating

Confidence Assessment Format

Each phase skill writes a ## Confidence Assessment section at the bottom of its artifact:

## Confidence Assessment
- **Level**: high | medium | low
- **Score**: <0-100 integer>
- **Score rationale**: <1-2 sentences>
- **Open questions**: <bullet list, or "None">

Confidence Flow

After each phase completes, read the confidence level from the artifact:

Confidence Threshold Action
High >=90% Advance to next phase silently
Medium 70-89% Post JIRA comment with findings and open questions, then advance
Low <70% Post JIRA comment, then stop and escalate via AskUserQuestion

Read the full file on GitHub · 208 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. 2d ago First seen · 208 lines · 41 tokens per session scan A 0c01e562d0a6

Subscribe to this mod's changes

controller is a skill published in the GitHub repository quay/ai-helpers (3 stars, last pushed 19d ago), licensed MIT. It adds 41 tokens to every session and 1,586 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.

Related

Other skills, from other repositories

systematic-debugging

4-phase root cause debugging: understand bugs before fixing.

NousResearch/hermes-agent · 16 tokens

langsmith-observability

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

davila7/claude-code-templates · 45 tokens

experimental-code-coverage-local-debugger

Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.

chromium/chromium · 59 tokens

adversarial-reviewer

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

emdash-cms/emdash · 71 tokens

cli-e2e

Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.

ComposioHQ/composio · 62 tokens

ios-simulator

Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.

callstack/agent-device · 69 tokens