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 agentmods add skills/madappgang/magus/deep-analysisnpx skills add MadAppGang/magus --skill deep-analysisgit 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/deep-analysis)<a href="https://agentmods.dev/skills/madappgang/magus/deep-analysis"><img src="https://agentmods.dev/badge/skills/madappgang/magus/deep-analysis.svg" alt="Measured on agentmods" 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 | $0.01694 |
| Opus 5 | $0.00022 | $0.00847 |
| Sonnet 5 | $0.00009 | $0.00339 |
| Haiku 4.5 | $0.00004 | $0.00169 |
Grade A, and why
deep-analysis 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 6d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep analysis
A multi-dimensional audit. Retrieval mechanics live in the code-search skill and
single-thread investigation in investigate; this skill is the dimension set, the verdict
definitions, and the report contract.
When this is the right depth
- A review asked for as comprehensive, full, or end-to-end
- A bug that crosses more than one system
- A major refactor or an architecture decision record
- Tech-debt assessment and prioritisation
- Onboarding someone to an unfamiliar codebase
- Post-incident root-cause analysis
- A security audit
- One dimension was already investigated and proved insufficient
Discipline
- Never rank-truncate a result set — narrow with
scope, not withhead. - An error and an empty result mean opposite things. Establish which you have.
- A clean result is a finding. "No dead code found" is evidence of hygiene; report it with the threshold that produced it rather than dropping it.
- Validate relevance, not just success. If none of the query's key terms appear in the results, reformulate rather than build on them.
- Name the method behind every finding, including the dimensions where lexical search was the correct tool.
- Blocked, never stalled. A subagent cannot ask the user a question. Return a result
beginning
BLOCKED:naming what is missing and what would unblock it, and let the dispatching orchestrator ask. - Centrality is relative — tiers, not numbers. An absent centrality means unknown.
The seven dimensions
| # | Dimension | Question | Primary signal |
|---|---|---|---|
| 1 | Architecture | What is the shape, and what are its pillars? | Highest-centrality symbols are the architecture. Layers from presentation / business / data vocabularies; patterns from factory, interface, event vocabularies |
| 2 | Implementation | How does the critical path actually run? | Outbound edges of the high-centrality symbols (dependencies), inbound edges of the critical functions (usage), full context for the complex ones |
| 3 | Test coverage | What is untested that matters? | Inbound edges filtered to test files. High centrality plus zero test callers = critical gap |
| 4 | Reliability | How does it fail, and does it recover? | Error-handling chains via full context; exception flow via throw/error/exception vocabulary; inbound edges of custom error types; retry/fallback/circuit-breaker vocabulary |
| 5 | Security | Where are the trust boundaries? | Authentication entry points with both edge directions; authorization via permission/role/guard vocabulary; sensitive data via password/hash/token/secret vocabulary; inbound edges of encryption |
| 6 | Performance | What is structurally slow? | Database and batch query patterns, async and parallel patterns, cache and memoize patterns |
| 7 | Code health | What is rotting? | Dead code split by centrality, and test gaps with the full impact pulled for the critical ones |
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.
- 6d ago First seen · 142 lines · 43 tokens per session scan A bb72388bc74a
deep-analysis is a skill published in the GitHub repository MadAppGang/magus (9 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 1,694 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
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…