A bug-debugging workflow for diagnosing unexpected behavior, planning a fix, and carrying it through to completion.

Use it to investigate bugs, run deep debugging, delegate diagnosis, and classify the returned result.

It provides a defined path from an error report to a diagnosis and fix, including optional delegation to another coding host.

bugfix — Skill for Claude Code by kangig94/coral

Install

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.

Any agent

npx skills add kangig94/coral --skill bugfix

Clone the repo

git clone --depth 1 https://github.com/kangig94/coral

Made for: Claude Code.

Or install coral, the plugin that ships this one along with the rest of its 12 skills, 10 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kangig94/coral/bugfix/github.svg)](https://agentmods.dev/skills/kangig94/coral/bugfix)

Your own site

<a href="https://agentmods.dev/skills/kangig94/coral/bugfix"><img src="https://agentmods.dev/badge/skills/kangig94/coral/bugfix/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kangig94/coral/bugfix"><img src="https://agentmods.dev/badge/skills/kangig94/coral/bugfix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 838 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.

Model	Per session	Once invoked
Fable 5.1	$0.00020	$0.00838
Opus 5.5	$0.00008	$0.00335
Sonnet 5.5	$0.00004	$0.00168
Haiku 4.5	$0.00002	$0.00084

Measured today against content hash e9b1647418b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bugfix 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 today.

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.

clients/skills/bugfix/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug Debugging

Diagnose bugs, plan fixes, and execute - end-to-end.

Argument Routing

Argument	Mode
`<prompt>`	Self-execute on current host (default)
`--delegate`	Delegate to the other host (Claude → Codex, Codex → Claude, Copilot → Codex; current host comes from SessionStart `Current host:`)
`--delegate <prompt>`	Same with prompt

Strip the --delegate flag before passing the prompt to the execution path.

Execution

Diagnose:
- Self-execute (default): Spawn Agent({ subagent_type: "coral:debugger", prompt: "--deep " + prompt }). Wait for the agent to return its diagnosis in <Output_Format> structure.
- Delegate (--delegate): Run coral-cli <other-host> debugger --work-dir "<work_dir>" -d -i - <<'CORAL_INPUT' with the <--deep prompt> as the body of that quoted heredoc, closed by a CORAL_INPUT line (<other-host> = the delegation target for the current host: Claude → Codex, Codex → Claude, Copilot → Codex). Capture job from Provider job <jobId> execution #<n> <launchState>, then run cd "<work_dir>" && coral-cli jobs wait <job> --embed. Classify the result from its rendered output, not exit code 75 alone: Result path: <path> marks a terminal result, so read that artifact and stop waiting even when a terminal provider_exit propagated code 75; a status beginning Still waiting with (cursor: <cursor>) means the job is still live, so run the printed continuation command exactly as printed, from the same cwd. If an error prints remediation:, follow it only when it contains a coral-cli jobs wait command, preserving all arguments and the same cwd; accept either backticked or plain-text commands, exclude surrounding prose, and use a background shell when instructed. Otherwise stop and surface the rendered error. wait_build_mismatch requires restarting the session. A non-zero provider_exit code is terminal and is passed through unchanged (0–255). On error, stop with the error message. Verify cited file:line references. Drop findings with incorrect references.

Read the full file on GitHub · 46 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.

today Changed e9b1647418b8
5d ago Changed e3860e69d7f2
15d ago Changed d844bf482eaf
29d ago Changed 5f4af87cb34e
1mo ago First seen · 46 lines · 20 tokens per session scan A fde7936870c8

Subscribe to this mod's changes

bugfix is a skill published in the GitHub repository kangig94/coral (11 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 838 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude Code Debugging ai-agents claude plugin vibe-coding

hns-lsel-curator

Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…

modu-ai/moai-adk · 135 tokens

moai-workflow-ddd

Domain-Driven Development workflow specialist using ANALYZE-PRESERVE-IMPROVE cycle for behavior-preserving code transformation. Use when refactoring legacy code or reducing technical debt safely.

modu-ai/moai-adk · 44 tokens

moai-lane-watchdog

One lane stall watchdog iteration: measure lane progress on three channels, classify the stall cause, apply the remedy or resolve the judgment through the decision ladder — instead of waiting on a reply — then record the outcome and report. Reads the unified --auto doctrine at…

modu-ai/moai-adk · 86 tokens

cherry-assistant-guide

A guide for looking up Cherry Studio's product details and diagnosing problems such as connection failures, setup errors, and runtime issues.

CherryHQ/cherry-studio · 68 tokens

cherry-electron-dev

Develop, fix, profile, and test PRs in a tracked Cherry Studio Electron instance. Use for implementation, UI and interaction work, runtime debugging, DevTools inspection, performance analysis, and interactive PR verification with a test report. Reuse a verified workspace instance and manage its lifetime according to…