Borrowing it
Nothing to install: this file belongs to Smart-AI-Memory/attune-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Smart-AI-Memory/attune-ai/main/.agents/skills/bug-predict/SKILL.mdgit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote 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/skills/smart-ai-memory/attune-ai/bug-predict)<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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 46 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00040 | $0.00647 |
| Opus 5.5 | $0.00016 | $0.00259 |
| Sonnet 5.5 | $0.00008 | $0.00129 |
| Haiku 4.5 | $0.00004 | $0.00065 |
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 1mo 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 — 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:
- Target path: "Which files or directory should I
scan?" Default to
src/if not specified. - 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.
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.
- 1mo ago Changed · +13 lines eefd82eac36d
- 1mo ago First seen · 68 lines · 40 tokens per session scan A a4832663aba7
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 5.5. 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.
Other skills, from other repositories
ripple
Analyzing pre-change impact across vertical (dependency chains, files) and horizontal (pattern consistency, naming) dimensions. Use to estimate blast radius before a refactor. No code.
sweep
Detecting unnecessary files, unused code, and orphaned files, and proposing safe deletion. Not for removal execution (Builder), repo structure (Grove), or scope cutting (Void).
bolt
Optimizing frontend (re-render, memoization, lazy loading) and backend (N+1, indexing, caching, async) performance, plus continuous auto-tuning loops for GC/threadpool/cache/worker settings.
lens
Comprehending and investigating codebases: structure mapping, feature discovery, data flow tracing for 'does X exist?' or 'how does Y work?'. Includes a conversational ask mode. Does not write code.
scout
Investigating bugs via root cause analysis, reproduction steps, and impact assessment. Investigation-only — finds why bugs occur and where to fix them, no code. Use when a bug needs RCA before a fix.
trail
Investigating git history, analyzing regression root causes, and performing code archaeology. Time-travels through commits to uncover truth. Use for git history investigation.