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 investigategit 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/investigate)<a href="https://agentmods.dev/skills/madappgang/magus/investigate"><img src="https://agentmods.dev/badge/skills/madappgang/magus/investigate/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/investigate"><img src="https://agentmods.dev/badge/skills/madappgang/magus/investigate.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 | $0.00043 | $0.02091 |
| Opus 5 | $0.00022 | $0.01045 |
| Sonnet 5 | $0.00009 | $0.00418 |
| Haiku 4.5 | $0.00004 | $0.00209 |
Grade A, and why
investigate 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigate
One investigation, one mode. Pick the mode from the request, announce it, then run that
mode's sequence. The retrieval mechanics live in the code-search skill; this skill is
about which questions to ask and in what order.
Routing
| Mode | Trigger keywords | Question sequence |
|---|---|---|
| Bug | debug, error, broken, failing, crash | full context → inbound → outbound → transitive impact |
| Test gap | test, coverage, edge case, mock | inbound filtered to test files → gap detection |
| Architecture | architecture, design, structure, layer | structural map → centrality → dependency closure |
| Implementation (default) | how does, implementation, data flow | locate → inbound → outbound → full context |
Collision order: Bug > Test > Architecture > Implementation. No keyword matches → Implementation.
Announce the routing before executing it — print the query, the chosen mode, and the one-line reason. A wrong route is then correctable in one turn instead of after the investigation is spent.
Discipline that applies to every mode
- Never rank-truncate a result set. Ranking already put the important results first;
cutting by line count deletes them. Narrow with
scopeinstead. - An error and an empty result look alike and mean opposite things. Establish which one you have before you report either.
- Name the method behind every finding. Lexical search is the right tool for exact strings, counts and filename patterns — using it is routing, not a fallback. Using it without saying so is the defect.
- Blocked, never stalled. A subagent has no tool for asking the user a question. If you
cannot proceed, do not wait for an answer that cannot arrive and do not decide on the
user's behalf: return a result beginning
BLOCKED:naming what is missing and what would unblock it, and let the dispatching orchestrator ask. - Centrality is relative. Treat it as tiers — core, key, ordinary, leaf — never as a number to threshold. An absent centrality means unknown, not low.
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 · 208 lines · 43 tokens per session scan A cc65e525505d
investigate is a skill published in the GitHub repository MadAppGang/magus (9 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 2,091 once invoked, about $0.0002 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
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…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.