Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MadAppGang/magus/plugin install devWrote 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/context-detection)<a href="https://agentmods.dev/skills/madappgang/magus/context-detection"><img src="https://agentmods.dev/badge/skills/madappgang/magus/context-detection/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/context-detection"><img src="https://agentmods.dev/badge/skills/madappgang/magus/context-detection.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 | $0.00053 | $0.06092 |
| Opus 5.5 | $0.00021 | $0.02437 |
| Sonnet 5.5 | $0.00011 | $0.01218 |
| Haiku 4.5 | $0.00005 | $0.00609 |
Grade A, and why
context-detection 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 20d 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 — 793 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Detection Skill
Scope: this skill maps EVIDENCE to STACK. It does not map stack to skill
The line matters, and it is the whole reason this file was rewritten.
| Question | Answered in |
|---|---|
| Which stacks is this repo built from, and what proves it? | here |
| Which paths should agent X read for task Y? | references/loadout-rules.md |
| What shape does the emitted artifact take? | references/context-schema.md |
This file used to answer all three. It carried a bash generate_skill_paths() and a
map_stacks_to_skills() table, and plugins/dev/agents/stack-detector.md carried the same
mapping again in XML. Two hand-maintained copies, both loaded on nearly every dev entry
point — this skill is preloaded by ten commands — so when one went stale, it went stale
twice. A skill path that had never existed shipped in both.
Both copies are gone. Stack→skill mapping now has exactly one home,
references/loadout-rules.md, and skill paths are derived from the filesystem at detection
time rather than recalled from a table. Do not reintroduce a table here, in any language,
in any fence.
Quick Start: Skill Discovery Script
Run the helper script to discover ALL skills available to a project:
node "${CLAUDE_PLUGIN_ROOT}/skills/context-detection/scripts/discover-skills.js" "$(pwd)"
This searches all 7 official Claude Code skill locations:
- Personal:
~/.claude/skills/ - Project:
.claude/skills/ - Nested (monorepos):
**/.claude/skills/ - Legacy commands:
.claude/commands/ - Marketplace plugins:
~/.claude/plugins/marketplaces/{m}/plugins/{p}/skills/ - Local plugins:
.claude-plugin/skills/,plugins/*/skills/ - Enterprise (managed settings)
Output: JSON with summary stats and full skill metadata.
For detailed documentation on the script, see scripts/discover-skills.js.
Overview
The context detection skill provides systematic patterns for analyzing any project to determine its technology stack(s). It enables the dev plugin to auto-load appropriate framework-specific skills based on what's actually in the project.
What ships with it
3 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.
- 20d ago Changed · +11 lines f319967fa439
- 22d ago Changed · +1 lines f8d59c05791c
- 1mo ago Changed · -84 lines 98712312f83b
- 1mo ago First seen · 865 lines · 53 tokens per session scan A ab8b18bdf072
context-detection is a skill published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 6,092 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 2026-09-04.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…