Borrowing it
Nothing to install: this file belongs to richardwooding/file-search-on. 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/richardwooding/file-search-on/main/.claude/skills/file-search-on-mcp/SKILL.mdgit clone --depth 1 https://github.com/richardwooding/file-search-onWrote 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/richardwooding/file-search-on/file-search-on-mcp)<a href="https://agentmods.dev/skills/richardwooding/file-search-on/file-search-on-mcp"><img src="https://agentmods.dev/badge/skills/richardwooding/file-search-on/file-search-on-mcp/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/richardwooding/file-search-on/file-search-on-mcp"><img src="https://agentmods.dev/badge/skills/richardwooding/file-search-on/file-search-on-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector 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 | $0.00327 | $0.04280 |
| Opus 5 | $0.00163 | $0.02140 |
| Sonnet 5 | $0.00065 | $0.00856 |
| Haiku 4.5 | $0.00033 | $0.00428 |
Grade A, and why
file-search-on-mcp 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 12d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
file-search-on MCP
file-search-on is a content-type-aware file search exposed as a Model Context Protocol server. Once registered with an MCP client, it gives an agent typed access to file metadata — not just paths and bytes but image EXIF, PDF page counts, audio bitrates, source-code LOC, archive entries, email headers, GPS coordinates, git-aware churn / authorship, and so on — through 43 tools driven by a CEL expression language.
This skill is the agent-facing usage guide. The codebase ships at github.com/richardwooding/file-search-on. The MCP launch shape is file-search-on mcp (stdio for desktop clients) or file-search-on mcp --transport http --addr :8080 (Streamable HTTP). The skill assumes the server is already running and registered with the client.
When to reach for this MCP
| Question shape | Use |
|---|---|
"Find files named X" or "paths matching a glob" |
Glob |
"Find files containing literal text X" (single regex over plain files) |
Grep |
| "Find files by attribute — biggest videos, photos near a GPS bbox, source with > 200 LOC, PDFs with > 10 pages, drafts older than 90 days" | this MCP — search |
| "What's in this folder?" — count by content type / language / camera / extension | this MCP — stats |
| "Find duplicates" (byte-identical) or near-duplicates (typo-edit / template) | this MCP — find_duplicates / find_near_duplicates |
| "Find regex hits with surrounding context" pruned by attribute | this MCP — find_matches |
| "What's in tree A but not in tree B?" | this MCP — diff_trees |
| "What project does this path belong to?" | this MCP — detect_project / find_projects / resolve_project_for_path |
| "Conceptual / paraphrase-tolerant search" via embeddings | this MCP — search_semantic |
| "Who imports / calls / defines X?", "blast radius of changing Y", "how does A reach B?" | this MCP — code graph: imported_by / who_calls / calls / find_definition / references / impact / call_path / trace |
| "Where's the architectural risk?" — coupling, circular deps, complexity hotspots, dead code, untested code, over-exports | this MCP — coupling / circular / complexity / dead_code / test_gaps / coverage_gaps / unused_exports |
| "Gate this commit / PR" — fail on over-complex or dead code in the diff | this MCP — review |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 181 lines · 327 tokens per session scan A f97551a41a4c
file-search-on-mcp is a skill published in the GitHub repository richardwooding/file-search-on (5 stars, last pushed 3d ago), licensed MIT. It adds 327 tokens to every session and 4,280 once invoked, about $0.0016 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 2026-08-31.
Other skills, from other repositories
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
write-zot-themes
Help the user create, install, or package zot themes, including theme-only extensions.
gograph
Go repository intelligence for Claude Code. Use when reading, navigating, editing, reviewing, or refactoring a Go codebase. Exposes 64 query, analysis, and workflow capabilities through the local gograph MCP server, including bounded first-call exploration, AST-aware call graphs, blast-radius analysis, impact, and…
bubbletea-testing
Use this skill whenever writing tests for Bubble Tea (charmbracelet/bubbletea) TUI applications in Go. Triggers include any mention of testing Bubble Tea models, teatest, golden file testing for TUIs, testing tea.Cmd or tea.Msg, snapshot testing terminal output, or writing tests for any Go CLI/TUI that uses the Elm…
pi-loop-forensics
Diagnose pi-go agent loops and degenerate turns — "agent loop aborted", runaway thinking with no tool calls, repeated phrases. Discriminates genuine model repetition collapse from a race, a tool-parse failure, or a too-low guard, and A/B replays a seed session across providers.
vhs-e2e-gif
Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit. Use when asked to record an e2e run, demo a fix on a PR, attach a GIF or screen recording to a pull request, show a test passing visually, or produce a terminal…