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 roshunsunder/filesift --skill search-codebasegit clone --depth 1 https://github.com/roshunsunder/filesiftWrote 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/roshunsunder/filesift/search-codebase)<a href="https://agentmods.dev/skills/roshunsunder/filesift/search-codebase"><img src="https://agentmods.dev/badge/skills/roshunsunder/filesift/search-codebase/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/roshunsunder/filesift/search-codebase"><img src="https://agentmods.dev/badge/skills/roshunsunder/filesift/search-codebase.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00074 | $0.01641 |
| Opus 5.5 | $0.00030 | $0.00656 |
| Sonnet 5.5 | $0.00015 | $0.00328 |
| Haiku 4.5 | $0.00007 | $0.00164 |
Grade A, and why
search-codebase 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 1mo 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Searching Codebases with FileSift
FileSift indexes codebases and enables natural language search via hybrid keyword (BM25) + semantic (FAISS embeddings) search, merged with Reciprocal Rank Fusion.
When to use this skill
Use FileSift when the target is a concept or behaviour, not a known identifier.
Reach for FileSift when:
- You're in the exploration phase of a task and need to orient yourself in an unfamiliar codebase
- The user asks a question that requires understanding what code does ("how is auth handled?", "where does billing happen?", "what validates user input?")
- You need to find an implementation but don't know what it's called — you'd have to guess grep patterns
- You're looking for the files most relevant to a concept that could be expressed many ways (
retry,backoff,exponential_sleep,with_retries…) - You've read one relevant file and want to find its collaborators by semantic proximity
Prefer grep / glob instead when:
- You already know the exact function name, class name, or string to search for
- You're tracing a known call chain or import path
- The search is purely structural (file extensions, directory layout, naming conventions)
- The codebase is small enough that a directory listing gives you the full picture
The rule of thumb: if you'd have to guess the right grep pattern, FileSift will outperform it. If you already know the exact token, grep is faster.
Step 0 — Verify FileSift is installed
Do this before anything else, every time this skill is invoked for the first time in a session.
filesift --version
If the command is found, proceed to Quick start.
If it isn't found, install it. FileSift requires Python 3.12+ and is published on PyPI. The right install command depends on how the user manages Python packages. Always ask the user before running any installation commands.
| Environment | Install command |
|---|---|
| pip (default) | pip install filesift |
| uv (tool) | uv tool install filesift |
| uv (project) | uv add filesift |
| pipx | pipx install filesift |
| poetry | poetry add filesift |
| pdm | pdm add filesift |
| conda / mamba | pip install filesift (inside the active conda env) |
What ships with it
1 file 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.
- 1mo ago First seen · 145 lines · 74 tokens per session scan A b791446e6b63
search-codebase is a skill published in the GitHub repository roshunsunder/filesift (6 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 74 tokens to every session and 1,641 once invoked, about $0.0003 per session on Opus 5.5. 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.