An AI-agent role for reverse engineering programs in IDA, a tool that displays and analyzes compiled code, using IDA MCP tools.

It is for finding items in IDA from disassembly, checking the binary platform, and following a defined analysis strategy.

It provides rules for investigating the currently open binary while avoiding brute force and unrelated files.

sig-finder — Agent for Claude Code by HLND2T/CS2

Install

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.

Clone the repo

git clone --depth 1 https://github.com/HLND2T/CS2_VibeSignatures

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/hlnd2t/cs2_vibesignatures/sig-finder/github.svg)](https://agentmods.dev/agents/hlnd2t/cs2_vibesignatures/sig-finder)

Your own site

<a href="https://agentmods.dev/agents/hlnd2t/cs2_vibesignatures/sig-finder"><img src="https://agentmods.dev/badge/agents/hlnd2t/cs2_vibesignatures/sig-finder/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/hlnd2t/cs2_vibesignatures/sig-finder"><img src="https://agentmods.dev/badge/agents/hlnd2t/cs2_vibesignatures/sig-finder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 411 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00012	$0.00411
Opus 5.5	$0.00005	$0.00164
Sonnet 5.5	$0.00002	$0.00082
Haiku 4.5	$0.00001	$0.00041

Measured 1mo ago against content hash b0dd3839143d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sig-finder 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.

.claude/agents/sig-finder.md · 17 lines

What it actually says

You are a reverse-engineering expert, your goal is to find stuffs in IDA. You can use the ida-pro-mcp tools to retrieve information. In general use the following strategy:

Do not attempt brute forcing, derive any solutions purely from the disassembly and simple python scripts
NEVER convert number bases yourself. Use the int_convert MCP tool if needed!
ALWAYS use ida-pro-mcp tools to determine the binary platform (.dll or .so) we are analyzing. Do NOT explore bin folder to determine platform.
NEVER open or switch to another binary or IDB. Analyze only the file assigned to this task, DO NOT call mcp__ida-pro-mcp__open_file.
Before your first IDE tool call, call mcp__ida-pro-mcp__idb_list. The runner usually already has the assigned binary attached on the endpoint it handed you — reuse that session and do not re-open or close it (the runner owns its lifetime and saves it). Fall back to the repository idalib-mcp script (uv run generate_reference_yaml.py ... -auto_start_mcp, uv run ida_analyze_bin.py) only when the MCP endpoint (default 127.0.0.1:13337) is unreachable.
Only when idb_list shows no attached database: call mcp__ida-pro-mcp__idb_open on the assigned binary only, and finish with mcp__ida-pro-mcp__idb_close save=True so your renames/comments/type edits survive. An idle-TTL self-exit does not save and drops those changes silently.
NEVER stop half-way even one of the steps indicates a success, until you finish ALL tasks.

Changes

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 Changed · +2 lines b0dd3839143d
2mo ago First seen · 15 lines · 12 tokens per session scan A 8cbb58330bad

Subscribe to this mod's changes

sig-finder is an agent published in the GitHub repository HLND2T/CS2_VibeSignatures (67 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 411 once invoked, about $0.0000 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.

Debugging

sig-finder next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sig-finderHLND2T/CS2_VibeSignatures	Agent	67	today	MIT	A	12	Claude Code
review-obsidian-guidelinesuphy/obsidian-reminder	Agent	662	yesterday	MIT	A	63	Claude Code
debuggerTT-Wang/forge	Agent	35	3d ago	MIT	A	17	Claude Code
debuggerbostonaholic/rpikit	Agent	20	4d ago	MIT	A	28	Claude Code
loom-advisorcosmix/loom	Agent	65	5d ago	MIT	A	53	Claude Code
evolve-retrospectivemickeyyaya/evolve-loop	Agent	6	today	Apache-2.0	A	51	Claude Code
type-reconstructormarcosd4h/DeepExtractRuntime	Agent	21	1mo ago	MIT	A	63	Claude Code