Help us improve
Share bugs, ideas, or general feedback.
From agent-guardrails
Scans Claude Code session logs for recurring agent anti-patterns like hedging, stalling, skipping, false completions, preference-asking, and dismissing; produces ranked reports with frequency counts, excerpts, and guardrail rule suggestions.
npx claudepluginhub florianbuetow/claude-code --plugin agent-guardrailsHow this skill is triggered — by the user, by Claude, or both
Slash command
/agent-guardrails:analyzeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Scan Claude Code session logs to detect recurring anti-patterns in assistant responses. Produce a ranked frequency report with excerpts and ready-to-use guardrail rule suggestions.
Analyzes Claude Code JSONL transcripts to detect anti-patterns, tool misuse, user frustration signals, and workflow patterns using DuckDB SQL, 10 dimensions, and PM4Py mining.
Analyzes Claude Code sessions using MCP classifiers to detect usage patterns like correction spirals, rates severity, and provides concrete workflow improvements with metrics and advice.
Analyzes Claude Code session logs to extract tool usage stats, thinking blocks, error patterns, debug trajectories, and generate actionable productivity recommendations. Provides cc-session CLI for overviews, timelines, searches.
Share bugs, ideas, or general feedback.
Scan Claude Code session logs to detect recurring anti-patterns in assistant responses. Produce a ranked frequency report with excerpts and ready-to-use guardrail rule suggestions.
The canonical regex patterns live in the plugin's rules/ directory — one .md file per category. Always read the patterns from those files rather than hardcoding them, so analysis stays in sync with installed/refined rules.
Source of truth: ${CLAUDE_PLUGIN_ROOT}/rules/no-*.md
Read each rule file's YAML frontmatter to extract the name, pattern, and message fields. The six categories are:
| # | Category | Rule file |
|---|---|---|
| 1 | Speculative Language | no-speculative-language.md |
| 2 | Stalling | no-stalling.md |
| 3 | Preference-Asking | no-preference-asking.md |
| 4 | False Completion | no-false-completion.md |
| 5 | Skipping | no-skipping.md |
| 6 | Dismissing | no-dismissing.md |
Scan for ALL of them plus any novel patterns discovered during analysis.
Find recent Claude Code session logs:
find ~/.claude/projects/ -name "*.jsonl" -mtime -7 ! -path "*/subagents/*" 2>/dev/null | head -30
If the user specifies a project or time range, narrow the search accordingly.
Create a Python script at /tmp/agent-guardrails-analyze.py that:
type: "assistant" entries where message.content[].type == "text"rules/ files (see table above)Script requirements:
--days N (default 7), --project PATH (optional filter)Format the analysis as a ranked report, inline in the response:
## Agent Guardrails Analysis Report
**Sessions scanned:** {count}
**Time range:** {oldest} to {newest}
**Total anti-pattern matches:** {total}
### Rankings (by frequency)
| # | Category | Matches | % of Total |
|---|----------|---------|------------|
| 1 | Speculative Language | 47 | 38% |
| 2 | Stalling | 28 | 23% |
| 3 | Preference-Asking | 21 | 17% |
| ... | ... | ... | ... |
### Category Details
#### 1. Speculative Language (47 matches)
**Top phrases:**
- "this should work" (12x)
- "I think" (9x)
- "probably" (8x)
**Example excerpts:**
> "...I think this change will fix the issue. The error was probably caused by..."
> "...this should work now. Let me know if..."
**Recommended rule:** Install via /agent-guardrails:install
---
[Continue for each category...]
After presenting the report, state which categories have the highest frequency and recommend running /agent-guardrails:install to install rules for them. Do not ask the user which ones they want — recommend based on the data.