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 MadAppGang/magus --skill searchgit clone --depth 1 https://github.com/MadAppGang/magusWrote 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/madappgang/magus/search)<a href="https://agentmods.dev/skills/madappgang/magus/search"><img src="https://agentmods.dev/badge/skills/madappgang/magus/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/madappgang/magus/search"><img src="https://agentmods.dev/badge/skills/madappgang/magus/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 | $0.00043 | $0.02255 |
| Opus 5.5 | $0.00017 | $0.00902 |
| Sonnet 5.5 | $0.00009 | $0.00451 |
| Haiku 4.5 | $0.00004 | $0.00226 |
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 22d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code search
Retrieval is cheap, reading is expensive. Every rule here moves work from the second into the first.
The tool surface
| Tool | Present | Arguments |
|---|---|---|
code_search |
always | query (free-form), intent, scope |
find_dependencies, find_dependents, call_tree, find_implementations, impact |
only when the configured engine genuinely supports the operation | symbol, depth / max_depth, scope |
Read, Grep, Glob |
always | — |
Read the tool list; never assume a structural tool exists. Absence means the engine cannot answer that class of question at all — not that it would be slow or approximate. When a tool you wanted is missing, say so in the report and answer with what is present.
code_search infers the intent from the query, so write the real question rather than a
hint. Pass intent only to override an inference you have watched go wrong.
Every response names the capability that served it. Read that field — it teaches the routing by example at no cost, and it is how you notice a substitution.
Classify before you query
| The request asks for | Kind | Route to |
|---|---|---|
| meaning, behaviour or a flow — "how does authentication work", "how does user data reach the database" | conceptual | code_search |
| the shape of the system, or where a named symbol lives and what it touches — "map the service layer", "find class UserService", "who calls parse" | structural | code_search, then the structural tools |
an exact literal, an occurrence count or a filename pattern — "find DEPRECATED_FLAG", "how many TODO comments", "all *.config.ts" |
lexical | Grep / Glob |
Locating a named symbol is structural, not lexical. Searching text for a class name returns every mention — comments, strings, imports — unranked, and still misses re-exports. Ask for the definition instead.
Lexical tools are the correct tool for the lexical row. That is routing, not a fallback and not a violation, and it needs no approval. What is forbidden is doing it silently: name the method you used.
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.
- 22d ago Changed 79eb1b48081f
- 1mo ago First seen · 177 lines · 43 tokens per session scan A 8c7c0b3fa7cd
search is a skill published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 2,255 once invoked, about $0.0002 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 2026-09-15.
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.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
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…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…