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 cyberkaida/reverse-engineering-assistant --skill deep-analysisgit clone --depth 1 https://github.com/cyberkaida/reverse-engineering-assistantWrote 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/cyberkaida/reverse-engineering-assistant/deep-analysis)<a href="https://agentmods.dev/skills/cyberkaida/reverse-engineering-assistant/deep-analysis"><img src="https://agentmods.dev/badge/skills/cyberkaida/reverse-engineering-assistant/deep-analysis/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/cyberkaida/reverse-engineering-assistant/deep-analysis"><img src="https://agentmods.dev/badge/skills/cyberkaida/reverse-engineering-assistant/deep-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 443 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00098 | $0.04988 |
| Opus 5.5 | $0.00039 | $0.01995 |
| Sonnet 5.5 | $0.00020 | $0.00998 |
| Haiku 4.5 | $0.00010 | $0.00499 |
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 1mo 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 — 608 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Analysis
Purpose
You are a focused reverse engineering investigator. Your goal is to answer specific questions about binary behavior through systematic, evidence-based analysis while improving the Ghidra database to aid understanding.
Unlike binary-triage (breadth-first survey), you perform depth-first investigation:
- Follow one thread completely before branching
- Make incremental improvements to code readability
- Document all assumptions with evidence
- Return findings with new investigation threads
Core Workflow: The Investigation Loop
Follow this iterative process (repeat 3-7 times):
1. READ - Gather Current Context (1-2 tool calls)
Get decompilation/data at focus point:
- get-decompilation (limit=20-50 lines, includeIncomingReferences=true, includeReferenceContext=true)
- find-cross-references (direction="to"/"from", includeContext=true)
- get-data or read-memory for data structures
2. UNDERSTAND - Analyze What You See
Ask yourself:
- What is unclear? (variable names, types, logic flow)
- What operations are being performed?
- What APIs/strings/data are referenced?
- What assumptions am I making?
3. IMPROVE - Make Small Database Changes (1-3 tool calls)
Prioritize clarity improvements:
rename-variables: var_1 → encryption_key, iVar2 → buffer_size
change-variable-datatypes: local_10 from undefined4 to uint32_t
set-function-prototype: void FUN_00401234(uint8_t* data, size_t len)
apply-data-type: Apply uint8_t[256] to S-box constant
set-decompilation-comment: Document key findings in code
set-comment: Document assumptions at address level
4. VERIFY - Re-read to Confirm Improvement (1 tool call)
get-decompilation again → Verify changes improved readability
5. FOLLOW THREADS - Pursue Evidence (1-2 tool calls)
Follow xrefs to called/calling functions
Trace data flow through variables
Check string/constant usage
Search for similar patterns
6. TRACK PROGRESS - Document Findings (1 tool call)
set-bookmark type="Analysis" category="[Topic]" → Mark important findings
set-bookmark type="TODO" category="DeepDive" → Track unanswered questions
set-bookmark type="Note" category="Evidence" → Document key evidence
What ships with it
2 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.
- 1mo ago First seen · 608 lines · 98 tokens per session scan A 622a5ab0622e
deep-analysis is a skill published in the GitHub repository cyberkaida/reverse-engineering-assistant (879 stars, last pushed today), licensed Apache-2.0. It adds 98 tokens to every session and 4,988 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
osgrep-reference
Comprehensive CLI reference and search strategies for osgrep semantic code search. Use for detailed CLI options, index management commands, search strategy guidance (architectural vs targeted queries), and troubleshooting. Complements the osgrep plugin which handles daemon lifecycle.
broadside
Interpret a Broad-Side batch reconnaissance run. Use after codecartobroadside collect has produced .codecarto/broadside/ / results, to triage scouting signals before or during an interactive CodeCartographer pipeline run.
scan-for-defects
Run a multi-pass defect scan across the source codebase, checking for logic errors, error handling gaps, concurrency bugs, security issues, API contract violations, and configuration hazards. Use after the architecture phase is complete. Optionally leverages contracts and protocols outputs for spec-grounded analysis.
scan-for-defects-semantic
Run the deep, semantic subset of the multi-pass defect scan — bugs that need contracts and protocols context to spot. Run after protocols, before porting. Covers concurrency and resource management, security and trust boundaries, and API contract violations (including state machine drift). The mechanical subset…
scan-for-defects-mechanical
Run the early, mechanical subset of the multi-pass defect scan — local bugs that do not need contracts or protocols context to spot. Run after the architecture phase, before contracts. Covers logic and correctness, error handling and resilience, and configuration and environment hazards. The semantic subset…
reverse-engineering-workbench
Coordinate EVOKORE reverse-engineering work across Ghidra-style static analysis, semantic recovery, and debugger-guided triage. Use when opening an unfamiliar binary, planning a decompilation workflow, or choosing between static and dynamic analysis paths.