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/claude-code --skill ultrathink-detectivegit clone --depth 1 https://github.com/MadAppGang/claude-codeWrote 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/claude-code/ultrathink-detective)<a href="https://agentmods.dev/skills/madappgang/claude-code/ultrathink-detective"><img src="https://agentmods.dev/badge/skills/madappgang/claude-code/ultrathink-detective/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/claude-code/ultrathink-detective"><img src="https://agentmods.dev/badge/skills/madappgang/claude-code/ultrathink-detective.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 | $0.00068 | $0.07752 |
| Opus 5 | $0.00034 | $0.03876 |
| Sonnet 5 | $0.00014 | $0.01550 |
| Haiku 4.5 | $0.00007 | $0.00775 |
Grade A, and why
ultrathink-detective 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 11d 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 — 893 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ultrathink Detective Skill
This skill uses ALL claudemem commands for comprehensive multi-perspective investigation.
Combines All Detective Perspectives
| Perspective | Focus | Commands Used |
|---|---|---|
| Architect | System design, layers | map, symbol |
| Developer | Implementation, flow | callers, callees |
| Tester | Coverage, gaps | callers for tests |
| Debugger | Root cause, chains | context |
Full command set:
claudemem --agent map "query"- Architecture overviewclaudemem --agent symbol <name>- Exact locationsclaudemem --agent callers <name>- Impact analysisclaudemem --agent callees <name>- Dependency tracingclaudemem --agent context <name>- Full call chainclaudemem --agent search "query"- Semantic search
Ultrathink Detective Skill
Version: 3.3.0 Role: Senior Principal Engineer / Tech Lead Model: Opus (for maximum reasoning depth) Purpose: Comprehensive multi-dimensional codebase investigation using ALL AST analysis commands with code health assessment
Role Context
You are investigating as a Senior Principal Engineer. Your analysis is:
- Holistic - All perspectives (architecture, implementation, testing, debugging)
- Deep - Beyond surface-level using full call chain context
- Strategic - Long-term implications from PageRank centrality
- Evidence-based - Every conclusion backed by AST relationships
- Actionable - Clear recommendations with priorities
Why Ultrathink Uses ALL Commands
| Command | Primary Use | Ultrathink Application |
|---|---|---|
map |
Architecture overview | Dimension 1: Structure discovery |
symbol |
Exact locations | Pinpoint critical code |
callers |
Impact analysis | Dimensions 2-3: Usage patterns, test coverage |
callees |
Dependencies | Dimensions 4-5: Data flow, reliability |
context |
Full chain | Bug investigation, root cause analysis |
search |
Semantic query | Dimension 6: Broad pattern discovery |
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.
- 11d ago First seen · 893 lines · 68 tokens per session scan A 6837791f4c3d
ultrathink-detective is a skill published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 68 tokens to every session and 7,752 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
gsd-ns-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.
dorodango
Polishes working code through successive quality passes in fresh subagents. Use after tests pass when code needs multi-dimension refinement before release.