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-search-tipsgit 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-search-tips)<a href="https://agentmods.dev/skills/yoanbernabeu/grepai-skills/grepai-search-tips"><img src="https://agentmods.dev/badge/skills/yoanbernabeu/grepai-skills/grepai-search-tips/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-search-tips"><img src="https://agentmods.dev/badge/skills/yoanbernabeu/grepai-skills/grepai-search-tips.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 | $0.00026 | $0.01617 |
| Opus 5 | $0.00013 | $0.00809 |
| Sonnet 5 | $0.00005 | $0.00323 |
| Haiku 4.5 | $0.00003 | $0.00162 |
Grade A, and why
grepai-search-tips 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 11d 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 — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GrepAI Search Tips
This skill provides tips and best practices for writing effective semantic search queries.
When to Use This Skill
- Improving search result quality
- Learning semantic search techniques
- Understanding how to phrase queries
- Troubleshooting poor search results
Semantic Search Mindset
Think differently from text search:
| Text Search (grep) | Semantic Search (GrepAI) |
|---|---|
| Search for exact text | Search for meaning/intent |
| "getUserById" | "retrieve user from database by ID" |
| Literal match | Conceptual match |
Query Writing Principles
1. Describe Intent, Not Implementation
❌ Bad: getUserById
✅ Good: fetch user record from database using ID
❌ Bad: handleError
✅ Good: error handling and response to client
❌ Bad: validateInput
✅ Good: check if user input is valid and safe
2. Use Descriptive Language
❌ Bad: auth
✅ Good: user authentication and authorization
❌ Bad: db
✅ Good: database connection and queries
❌ Bad: config
✅ Good: application configuration loading
3. Be Specific About Context
❌ Bad: validation
✅ Good: validate email address format
❌ Bad: parse
✅ Good: parse JSON request body
❌ Bad: send
✅ Good: send email notification to user
4. Use 3-7 Words
| Length | Example | Quality |
|---|---|---|
| Too short | "auth" | ⚠️ Vague |
| Good | "user authentication middleware" | ✅ Specific |
| Too long | "the code that handles user authentication and validates JWT tokens in the middleware layer" | ⚠️ Verbose |
5. Use English
Embedding models are trained primarily on English:
❌ authentification utilisateur (French)
✅ user authentication
Even if your code comments are in another language, English queries work best.
Query Patterns
Finding Code by Behavior
grepai search "validate user credentials before login"
grepai search "send notification when order is placed"
grepai search "calculate total price with discounts"
grepai search "retry failed HTTP requests"
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.
- 11d ago First seen · 305 lines · 26 tokens per session scan A 26a53bd3495a
grepai-search-tips is a skill published in the GitHub repository yoanbernabeu/grepai-skills (20 stars, last pushed 7mo ago), licensed MIT. It adds 26 tokens to every session and 1,617 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
codebase-search
Semantic code and documentation search by meaning. Use codebasepeek to find WHERE code is (saves tokens), codebasesearch to see actual code. For exact identifiers, use grep instead. Search local codebase before using websearch for code/library/API/example questions.
qdrant-advisor
Diagnose, troubleshoot, and advise on any Qdrant deployment by loading the latest official Qdrant skills live from skills.qdrant.tech. Use this whenever someone raises a Qdrant problem or question — slow or degraded search, high or growing memory / OOM crashes, optimizer stuck or slow, indexing slowness, scaling and…
qdrant-search-quality-diagnosis
Diagnoses Qdrant search quality issues. Use when someone reports 'results are bad', 'wrong results', 'not relevant results', 'missing matches', 'recall is low', 'approximate search worse than exact', 'which embedding model', 'quality dropped after quantization', 'how to measure retrieval quality', 'build a golden…
qdrant-monitoring-debugging
Diagnoses Qdrant production issues using metrics and observability tools. Use when someone reports 'optimizer stuck', 'indexing too slow', 'memory too high', 'OOM crash', 'queries are slow', 'latency spike', or 'search was fast now it's slow'. Also use when performance degrades without obvious config changes.
codebase-search
Preferred local codebase-understanding workflow for Pi and Codex. Start with codebasecontext before shell search or broad reads, then use specialized semantic and graph tools.
cocosearch-debugging
Use when debugging an error, unexpected behavior, or tracing how code flows through a system. Guides root cause analysis using CocoSearch semantic and symbol search.