bug-predict

bug-predict is a skill for Claude Code, Codex from Smart-AI-Memory/attune-ai. It costs 40 tokens per session (647 once invoked), scanned A, original, Apache-2.0.

A code-risk scanner that predicts likely bug locations from code patterns, complexity, and how often files change.

In plain words
What is it for?
It helps scan a directory or selected files, report likely bug hotspots, and filter findings by severity.
Why use it?
It helps focus debugging and review effort on areas most likely to contain defects.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/smart-ai-memory/attune-ai/bug-predict
Any agent
npx skills add Smart-AI-Memory/attune-ai --skill bug-predict
Clone the repo
git clone --depth 1 https://github.com/Smart-AI-Memory/attune-ai

Made for: Claude Code, Codex.

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 bug-predict

README.md
[![agentmods](https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/bug-predict.svg)](https://agentmods.dev/skills/smart-ai-memory/attune-ai/bug-predict)
Your own site
<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/bug-predict"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/bug-predict.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 647 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00040 $0.00647
Opus 5 $0.00020 $0.00324
Sonnet 5 $0.00008 $0.00129
Haiku 4.5 $0.00004 $0.00065

Measured yesterday against content hash eefd82eac36d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bug-predict 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 yesterday.

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.

.agents/skills/bug-predict/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug Prediction

IMPORTANT: Start your response with a context preamble.

Call help_lookup(topic="bug-predict", mode="preamble") and display the returned preamble text as a blockquote. Then tell the user they can say "tell me more" for a step-by-step guide, or answer the scoping questions below to proceed.

If the MCP call fails, fall back to:

Bug Predict — Predicts where bugs are most likely based on code patterns, complexity, and change frequency.

Scoping

Before running, ask:

  1. Target path: "Which files or directory should I scan?" Default to src/ if not specified.
  2. Severity filter: "Show all findings, or only HIGH severity?"

Execution

Call the bug_predict MCP tool with the scoped path:

bug_predict(path="<user-specified path>")

Or via CLI:

uv run attune workflow run bug-predict --path <target>

Shared command workspace (preferred)

When the generic command-workspace tools are available, open adapter bug-predict with the validated target path and all/high severity filter. The user's command invocation already authorizes this read-only scan: the workspace enters running state immediately and has no confirmation action. Run the existing bug_predict tool, publish optional progress, then publish one scan_result carrying the real success flag, risk score, findings, suggestions, or error. Present the terminal widget or its returned Markdown. A failed run must render did not complete, never a false zero-findings receipt. Fall back to the existing rich panel/Markdown behavior below when the shared tools are unavailable.

Output

Prefer the rich panel. If the tool response includes panel_html, pass it to mcp__visualize__show_widget — the universal report panel (title, score, findings/category sections; from attune.workflows.report_panel). It shows an explicit "did not complete" state on failure, never a false "clean". Fall back to the markdown below when the widget surface is unavailable.

Read the full file on GitHub · 81 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. yesterday Changed · +13 lines eefd82eac36d
  2. 4d ago First seen · 68 lines · 40 tokens per session scan A a4832663aba7

Subscribe to this mod's changes

bug-predict is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 647 once invoked, about $0.0002 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

tmux

Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).

Team-Commonly/commonly · 48 tokens

ship-and-babysit

End-to-end PR shipping workflow for tinyhumansai/openhuman: commit local changes, push to the user's fork, open or reuse a PR against main, then babysit CI and CodeRabbit feedback until the PR is green and clean. Use when the user asks to ship, open a PR, monitor CI, address review comments, or 'babysit' a branch.

tinyhumansai/openhuman · 83 tokens

lynkr

Universal LLM gateway with intelligent routing, Graphify code intelligence, Distill compression, routing telemetry, Code Mode, and 12+ provider support. 60-80% cost reduction for Claude Code, Cursor, and Codex.

Fast-Editor/Lynkr · 50 tokens

web-research

Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.

shibing624/agentica · 24 tokens

researchos-grow

Run one ResearchOS growth cycle: prime from L0/L1 → discover on user-trusted channels → capture → distill/corroborate by half-life → think → emit a lowest-burden user surface (act / hold / flip), audit behind. Use when the user wants to grow/deepen/research a topic.

lxinfei5/research-os · 71 tokens

officecli

Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.

Team-Commonly/commonly · 56 tokens