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.
npx skills add yoanbernabeu/grepai-skills --skill grepai-troubleshootinggit clone --depth 1 https://github.com/yoanbernabeu/grepai-skillsWrote 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/yoanbernabeu/grepai-skills/grepai-troubleshooting)<a href="https://agentmods.dev/skills/yoanbernabeu/grepai-skills/grepai-troubleshooting"><img src="https://agentmods.dev/badge/skills/yoanbernabeu/grepai-skills/grepai-troubleshooting/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/yoanbernabeu/grepai-skills/grepai-troubleshooting"><img src="https://agentmods.dev/badge/skills/yoanbernabeu/grepai-skills/grepai-troubleshooting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00025 | $0.03080 |
| Opus 5.5 | $0.00010 | $0.01232 |
| Sonnet 5.5 | $0.00005 | $0.00616 |
| Haiku 4.5 | $0.00003 | $0.00308 |
Grade E, and why
grepai-troubleshooting scanned grade E with 4 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 7d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/mcp.json Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
cat ~/.claude/mcp.json Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .grepai Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:11434/api/tags How it starts
The opening of the file, as written. The whole thing — 577 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GrepAI Troubleshooting
This skill provides solutions for common GrepAI issues and diagnostic procedures.
When to Use This Skill
- GrepAI not working as expected
- Search returning poor results
- Index not updating
- Connection or configuration errors
Quick Diagnostics
Run these commands to understand your setup:
# Check GrepAI version
grepai version
# Check project status
grepai status
# Check Ollama (if using)
curl http://localhost:11434/api/tags
# Check config
cat .grepai/config.yaml
Common Issues
Issue: "Index not found"
Symptom:
Error: Index not found. Run 'grepai watch' first.
Cause: No index has been created for this project.
Solution:
# Initialize if needed
grepai init
# Create the index
grepai watch
Issue: "Cannot connect to embedding provider"
Symptom:
Error: Cannot connect to Ollama at http://localhost:11434
Causes:
- Ollama not running
- Wrong endpoint configured
- Firewall blocking connection
Solutions:
- Start Ollama:
ollama serve
- Check endpoint in config:
embedder:
endpoint: http://localhost:11434 # Verify this
- Test connection:
curl http://localhost:11434/api/tags
Issue: "Model not found"
Symptom:
Error: Model 'nomic-embed-text' not found
Cause: The embedding model hasn't been downloaded.
Solution:
# Download the model
ollama pull nomic-embed-text
# Verify
ollama list
Issue: Search returns no results
Symptom: Searches return empty or very few results.
Causes:
- Index is empty
- Files are being ignored
- Query too specific
Solutions:
- Check index status:
grepai status
# Should show files > 0 and chunks > 0
- Verify files are being indexed:
# Check ignore patterns in config
cat .grepai/config.yaml | grep -A 20 "ignore:"
- Try broader query:
grepai search "function" # Very broad test
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.
- 7d ago Changed · +96 lines 854ca7cc49bd
- 2mo ago First seen · 481 lines · 25 tokens per session scan E ed980ac1a214
grepai-troubleshooting is a skill published in the GitHub repository yoanbernabeu/grepai-skills (20 stars, last pushed 8d ago), licensed MIT. It adds 25 tokens to every session and 3,080 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it E with 4 findings (reads agent configuration directories, reads mcp configuration, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
grepai-troubleshooting compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| grepai-troubleshootingyoanbernabeu/grepai-skills | Skill | 20 | 8d ago | MIT | E | 25 | Claude Code |
| codebase-searchHelweg/open-codebase-index | Skill | 230 | 3d ago | MIT | A | 38 | Claude Code |
| qdrant-advisorqdrant/skills | Skill | 267 | today | Apache-2.0 | A | 216 | Claude Code |
| qdrant-monitoring-debuggingqdrant/skills | Skill | 267 | today | Apache-2.0 | A | 75 | Claude Code |
| codebase-searchHelweg/open-codebase-index | Skill | 230 | 3d ago | MIT | A | 43 | Claude Code |
| cocosearch-debuggingVioletCranberry/coco-search | Skill | 37 | 4d ago | MIT | A | 37 | Claude Code |
| cocosearch-refactoringVioletCranberry/coco-search | Skill | 37 | 4d ago | MIT | A | 47 | Claude Code |