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 agentmods add skills/feniix/pi-extensions/code-searchnpx skills add feniix/pi-extensions --skill code-searchgit clone --depth 1 https://github.com/feniix/pi-extensionsWrote 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/feniix/pi-extensions/code-search)<a href="https://agentmods.dev/skills/feniix/pi-extensions/code-search"><img src="https://agentmods.dev/badge/skills/feniix/pi-extensions/code-search.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00023 | $0.00604 |
| Opus 5 | $0.00012 | $0.00302 |
| Sonnet 5 | $0.00005 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
code-search 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 3d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Search (Exa)
Use this skill when the user needs external coding context: official docs, API examples, error explanations, library comparisons, or implementation references that are not already in the repo.
Tool Selection
| Intent | Primary Tool | Notes |
|---|---|---|
| Find docs, examples, API syntax, or error reports | web_search_exa |
Start here for most lookups; include language/library/version in the query. |
| Read official docs or a promising result | web_fetch_exa |
Fetch 1-3 high-signal URLs after discovery. |
| Need a concise grounded explanation | web_answer_exa |
Best for direct questions; ask for citations and short code snippets. |
| Compare libraries or approaches across sources | web_research_exa |
Use only when enabled and the answer needs synthesis, not a quick lookup. |
| Find similar docs or examples from one strong page | web_find_similar_exa |
Use when a seed URL is clearly relevant. |
If web_research_exa or web_search_advanced_exa is unavailable, do not pretend it can be used. Fall back to web_search_exa plus selective web_fetch_exa.
Query Writing
- Include the language, framework/library, and version when known:
TypeScript 5.7 TypeBox Object additionalProperties. - Include exact identifiers, error strings, function names, or package names when available.
- Prefer official docs, release notes, issue trackers, and maintainer-authored examples before blogs.
- For debugging, include the error class/message and runtime context.
Recommended Parameters
web_search_exa{ "query": "TypeScript 5.7 TypeBox additionalProperties examples", "numResults": 5 }
web_fetch_exa{ "urls": ["https://example.com/docs/page"], "maxCharacters": 5000 }
web_answer_exa{ "query": "How does TypeBox validate additionalProperties in TypeScript?", "systemPrompt": "Prefer official docs and concise code snippets." }
web_research_exa{ "query": "Compare TypeScript runtime validation libraries for backend APIs, focusing on schema reuse, performance, and ergonomics.", "systemPrompt": "Prefer official docs, maintainer posts, and recent benchmarks. Call out uncertainty.", "outputSchema": { "type": "text" } }
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.
- 3d ago First seen · 47 lines · 23 tokens per session scan A f9873371503e
code-search is a skill published in the GitHub repository feniix/pi-extensions (23 stars, last pushed 10d ago), licensed MIT. It adds 23 tokens to every session and 604 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
cmux
Manage terminal sessions and browser surfaces via cmux — spawn workspaces for dev servers, test runners, background tasks, and embedded browsers. Read output, send commands, interact with web pages, and orchestrate multi-terminal workflows.
learn-codebase
Discover project conventions and surface security concerns. Use when starting work in a new or unfamiliar project, when asked to "learn the codebase", "check project rules", "what are the conventions", "onboard to this project", or "anything shady in this codebase". Scans agent config files (.claude/, .cursor/…
write-todos
Write clear, actionable todos that workers can execute without losing architectural intent. Use when "create todos", "write todos", "break into tasks", "plan todos", "make todos", or creating work items from a plan. Ensures each todo has unambiguous expected outcomes, concrete examples, and explicit constraints so…
self-improve
End-of-session retrospective that identifies improvements to agent config, tests, docs, and code. Use when asked to "self-improve", "reflect on session", "what can we improve", "session retrospective", "end of session review". Creates actionable todos from findings.
repotrace
Use repotrace as the local code intelligence layer before broad code exploration, nontrivial edits, impact analysis, route/call graph work, or architecture checks. Generates compact context bundles so coding agents do not get lost.
context-vault
Use a Markdown/Obsidian context vault for durable memory, workflow decisions, project lessons, context packs, SOPs, and cross-session handoffs.