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 paperfoot/search-cli --skill searchgit clone --depth 1 https://github.com/paperfoot/search-cliWrote 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/paperfoot/search-cli/search)<a href="https://agentmods.dev/skills/paperfoot/search-cli/search"><img src="https://agentmods.dev/badge/skills/paperfoot/search-cli/search/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/paperfoot/search-cli/search"><img src="https://agentmods.dev/badge/skills/paperfoot/search-cli/search.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 | $0.00100 | $0.01819 |
| Opus 5.5 | $0.00040 | $0.00728 |
| Sonnet 5.5 | $0.00020 | $0.00364 |
| Haiku 4.5 | $0.00010 | $0.00182 |
Grade A, and why
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 today.
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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
search
search "query" picks a mode, queries that mode's engines and returns one JSON
document (when piped, or with --json). Run search agent-info for every
command, flag, mode, engine and exit code.
Choosing a mode
The mode defaults to auto: fixed rules first (a lone URL is extract;
"tweets", "Twitter", "on X", x.com/ or a lone @handle is social, but
never code like @property or an email; similar to <URL> is similar;
"patent" or "prior art" is patents, never "patent leather"; "images of" is
images, never Docker or VM images), then JEV when logged in, else keyword
rules, else general. In news and social, a time word sets -f unless
you passed one ("today", "yesterday" → day;
"this week", "latest", "breaking" → week; "this month", "this year" →
month, year). Auto never picks deep, and picks social only on an X
cue: ask for those two with -m. An explicit -m or -p always wins; if the
-p engines cannot serve the mode auto picked, the search runs as general.
Pass -m when auto is not what you want:
| Task | Command |
|---|---|
| Anything on the web | search "…" (auto) or -m general |
| Current events | -m news -f day (or -f week) |
| Papers on a topic | -m academic |
| A paper's citations, versions, PDF | -m scholar |
| A person, their role, their LinkedIn | -m people |
| What X says about something | -m social |
| Read this page | -q <URL> -m extract; markdown is in results[0].snippet |
| Pages like this one | -q <URL> -m similar |
| Images | -m images; the picture is image_url, url is the page it is on |
| Local businesses | -m places |
| Prior art | -m patents |
| Wide coverage, cost no object | -m deep -c 30 (several times the price of general) |
Bare search "…" takes only the global flags (--json, --quiet, --x,
--last, --debug). A search flag after it (-m, -p, -c, -f, -d,
--no-cache and the rest) exits 3; use the full form:
search search -q "…" -m news -f week. -f takes day, week, month or
year; anything else exits 3.
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.
- today First seen · 128 lines · 100 tokens per session scan A d99e59df04f2
search is a skill published in the GitHub repository paperfoot/search-cli (58 stars, last pushed yesterday), licensed MIT. It adds 100 tokens to every session and 1,819 once invoked, about $0.0004 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 2026-11-03.
Other skills, from other repositories
r3f-animation
React Three Fiber animation - useFrame, useAnimations, spring physics, keyframes. Use when animating objects, playing GLTF animations, creating procedural motion, or implementing physics-based movement.
regulatory-audit-generator
Builds compliance checklists for business scenarios involving GDPR, PIPL, or advertising/data laws. Outputs a structured checklist with check items, legal basis, risk levels, and actionable recommendations. Triggered by requests like "run a compliance check," "GDPR/PIPL compliance," "pre-launch review," "privacy…
wordpress-penetration-testing
This skill should be used when the user asks to "pentest WordPress sites", "scan WordPress for vulnerabilities", "enumerate WordPress users, themes, or plugins", "exploit WordPress vulnerabilities", or "use WPScan". It provides comprehensive WordPress security assessment methodologies.
r3f-best-practices
React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.
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…
work-pipeline
Triggers the WORK-PIPELINE when a user request starts with a [] tag (e.g., [new-feature], [bugfix], [WORK start]). Use this skill whenever you detect a [] tag at the beginning of a user message.