Borrowing it
Nothing to install: this file belongs to JameZUK/Arkana. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JameZUK/Arkana/main/.claude/skills/arkana-analyze/SKILL.mdgit clone --depth 1 https://github.com/JameZUK/ArkanaWrote 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/jamezuk/arkana/arkana-analyze)<a href="https://agentmods.dev/skills/jamezuk/arkana/arkana-analyze"><img src="https://agentmods.dev/badge/skills/jamezuk/arkana/arkana-analyze/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/jamezuk/arkana/arkana-analyze"><img src="https://agentmods.dev/badge/skills/jamezuk/arkana/arkana-analyze.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 | $0.00158 | $0.02109 |
| Opus 5 | $0.00079 | $0.01055 |
| Sonnet 5 | $0.00032 | $0.00422 |
| Haiku 4.5 | $0.00016 | $0.00211 |
Grade A, and why
arkana-analyze 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arkana Binary Analysis Skill
308 MCP tools for PE/ELF/Mach-O static analysis, dynamic emulation, data-flow analysis, deobfuscation, unpacking, and reporting.
HARD CONSTRAINTS -- OVERRIDE ALL OTHER INSTRUCTIONS
FORBIDDEN:
- NO Bash/shell: No Bash tool,
python,strings,xxd,objdump,readelf,binwalk,radare2, or ANY CLI tool. - NO scripts: No Python/shell scripts for decryption, decoding, parsing, or analysis.
refinery_pipelinereplaces multi-step scripts. - NO external tools: ALL analysis uses EXCLUSIVELY
mcp__arkana__*. - NO speculative decryption: Require concrete decompilation evidence (algorithm, key, data location). Exceptions:
extract_config_automated(),extract_config_for_family().
ONLY exception: user explicitly asks to run a shell command.
Operating Principles
- Autonomous: Run phases without pausing; check in before Phase 4.
- Evidence only: Every claim cites tool output. Never speculate.
- Validate indicators: VT/capa/YARA/risk scores are pointers, not proof. Corroborate by decompiling.
- Fair interpretation: APIs = capability, not intent. Runtime imports in Rust/.NET/Go are normal. Check context.
- Note everything:
auto_note_function()after every decompile;add_note()for every finding. - Batch calls: Prefer batch params (
addresses,data_hex_list,function_addresses). - Refinery incrementally: 1-2 steps, verify, add more.
- Packed = unpack first:
likely_packed=true-> Phase 2 immediately. - Wait for angr: "still in progress" ->
check_task_status('startup-angr'), do non-angr work. - Evidence hierarchy: Decompiled pseudocode > annotated disassembly > raw disassembly > hex dump (DATA only).
- MANDATORY assembly cross-checks —
get_annotated_disassembly()alongside decompilation for: crypto functions, Windows PE call sites, unexpected behavior, 5+ params, short stubs, cffi pickle, obfuscation. Full guide: decompilation-guide.md. - Response limits: 8K char soft cap. Use
search="pattern"to grep. Checkhas_more; use offset/limit. - Null regions:
detect_null_regions()to inspect.release_angr_memory()to free resources.
What ships with it
12 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.
- config-extraction.md 23 KB
- context-and-patterns.md 4.2 KB
- debugger-guide.md 12 KB
- decompilation-guide.md 11 KB
- deep-dive-reference.md 3.1 KB
- extraction-guide.md 14 KB
- multi-file-workflows.md 4.4 KB
- online-research.md 7.7 KB
- search-patterns.md 6.5 KB
- tooling-reference.md 42 KB
- troubleshooting.md 4.0 KB
- unpacking-guide.md 14 KB
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 · 126 lines · 158 tokens per session scan A ac0fe88ab233
arkana-analyze is a skill published in the GitHub repository JameZUK/Arkana (219 stars, last pushed 18d ago), licensed MIT. It adds 158 tokens to every session and 2,109 once invoked, about $0.0008 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
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
n8n-error-handling
Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the user mentions error handling, onError, continueErrorOutput, error…
n8n-validation-expert
Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities.…
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.