Borrowing it
Nothing to install: this file belongs to HLND2T/CS2_VibeSignatures. 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/HLND2T/CS2_VibeSignatures/main/.claude/skills/generate-signature-for-function/SKILL.mdgit clone --depth 1 https://github.com/HLND2T/CS2_VibeSignaturesWrote 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/hlnd2t/cs2_vibesignatures/generate-signature-for-function)<a href="https://agentmods.dev/skills/hlnd2t/cs2_vibesignatures/generate-signature-for-function"><img src="https://agentmods.dev/badge/skills/hlnd2t/cs2_vibesignatures/generate-signature-for-function/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/hlnd2t/cs2_vibesignatures/generate-signature-for-function"><img src="https://agentmods.dev/badge/skills/hlnd2t/cs2_vibesignatures/generate-signature-for-function.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 | $0.00066 | $0.01771 |
| Opus 5 | $0.00033 | $0.00886 |
| Sonnet 5 | $0.00013 | $0.00354 |
| Haiku 4.5 | $0.00007 | $0.00177 |
Grade A, and why
generate-signature-for-function 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 10d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Signature for Function
Generate a unique hex byte signature for a function using fully programmatic wildcard detection and validation — no manual byte analysis required.
Prerequisites
- Function address (from decompilation, xrefs, or rename)
- IDA Pro MCP connection
Method
1. Generate and Validate Signature (Single Step)
Use a single py_eval call that:
- Resolves the input address to the actual function start
- Decodes instructions and programmatically determines wildcard positions
- Tracks instruction boundaries so prefixes always cover complete instructions
- Progressively tests at each instruction boundary via binary search
- Outputs the shortest unique signature directly
Note: The input address may be in the middle of a function. The script automatically resolves it to the actual function start.
mcp__ida-pro-mcp__py_eval code="""
import idaapi, ida_bytes, idautils, ida_ua, ida_segment, json
input_addr = <func_addr>
min_sig_bytes = 6
max_sig_bytes = 96
max_instructions = 64
# --- Binary search wrapper (IDA 9.0+ find_bytes -> older bin_search fallback) ---
def raw_bin_search(ea, max_ea, data, mask, flags=0):
if hasattr(ida_bytes, 'find_bytes'):
return ida_bytes.find_bytes(data, ea, range_end=max_ea, mask=mask, flags=flags)
return ida_bytes.bin_search(ea, max_ea, data, mask, len(data), flags)
# --- Resolve to actual function start ---
func = idaapi.get_func(input_addr)
if not func:
print(json.dumps({"error": f"{hex(input_addr)} is not inside a known function", "status": "failed"}))
raise SystemExit
func_addr = func.start_ea
if func_addr != input_addr:
print(f"NOTE: Resolved {hex(input_addr)} -> function start at {hex(func_addr)}")
# --- Collect instruction bytes with auto-wildcarding ---
limit_end = min(func.end_ea, func_addr + max_sig_bytes)
sig_tokens = []
inst_boundaries = [] # cumulative byte count at end of each instruction
cursor = func_addr
while cursor < func.end_ea and cursor < limit_end and len(sig_tokens) < max_sig_bytes:
insn = idautils.DecodeInstruction(cursor)
if not insn or insn.size <= 0:
break
raw = ida_bytes.get_bytes(cursor, insn.size)
if not raw:
break
wild = set()
# Auto-wildcard volatile operand bytes (imm/near/far/mem/displ)
for op in insn.ops:
op_type = int(op.type)
if op_type == int(idaapi.o_void):
continue
if op_type in (int(idaapi.o_imm), int(idaapi.o_near), int(idaapi.o_far), int(idaapi.o_mem), int(idaapi.o_displ)):
offb = int(op.offb)
if offb > 0 and offb < insn.size:
dsz = ida_ua.get_dtype_size(getattr(op, 'dtype', getattr(op, 'dtyp', 0)))
if dsz <= 0:
dsz = insn.size - offb
end = min(insn.size, offb + dsz)
for i in range(offb, end):
wild.add(i)
offo = int(op.offo)
if offo > 0 and offo < insn.size:
dsz2 = ida_ua.get_dtype_size(getattr(op, 'dtype', getattr(op, 'dtyp', 0)))
if dsz2 <= 0:
dsz2 = insn.size - offo
end2 = min(insn.size, offo + dsz2)
for i in range(offo, end2):
wild.add(i)
# Special handling for call/jump instructions
b0 = raw[0]
if b0 in (0xE8, 0xE9, 0xEB):
for i in range(1, insn.size):
wild.add(i)
elif b0 == 0x0F and insn.size >= 2 and (raw[1] & 0xF0) == 0x80:
for i in range(2, insn.size):
wild.add(i)
elif 0x70 <= b0 <= 0x7F:
for i in range(1, insn.size):
wild.add(i)
for idx in range(insn.size):
sig_tokens.append("??" if idx in wild else f"{raw[idx]:02X}")
inst_boundaries.append(len(sig_tokens))
cursor += insn.size
if not sig_tokens:
print(json.dumps({"error": f"no instruction bytes at {hex(func_addr)}", "status": "failed"}))
raise SystemExit
# --- Search bounds ---
seg = ida_segment.get_segm_by_name(".text")
if seg:
search_start, search_end = seg.start_ea, seg.end_ea
else:
search_start, search_end = idaapi.cvar.inf.min_ea, idaapi.cvar.inf.max_ea
# --- Progressive search at instruction boundaries only ---
best_sig = None
for boundary in inst_boundaries:
if boundary < min_sig_bytes:
continue
prefix_tokens = sig_tokens[:boundary]
if all(t == "??" for t in prefix_tokens):
continue
data = bytes(0 if t == "??" else int(t, 16) for t in prefix_tokens)
mask = bytes(0x00 if t == "??" else 0xFF for t in prefix_tokens)
flags = ida_bytes.BIN_SEARCH_FORWARD | ida_bytes.BIN_SEARCH_NOBREAK
matches = []
ea = raw_bin_search(search_start, search_end, data, mask, flags)
while ea != idaapi.BADADDR and len(matches) < 2:
matches.append(ea)
ea = raw_bin_search(ea + 1, search_end, data, mask, flags)
if len(matches) == 1 and matches[0] == func_addr:
best_sig = " ".join(prefix_tokens)
break
if best_sig:
print(json.dumps({
"func_va": hex(func_addr),
"func_rva": hex(func_addr - idaapi.get_imagebase()),
"func_size": hex(func.end_ea - func_addr),
"func_sig": best_sig,
"sig_bytes": len(best_sig.split()),
"status": "success"
}))
else:
print(json.dumps({
"func_va": hex(func_addr),
"func_size": hex(func.end_ea - func_addr),
"total_tokens": len(sig_tokens),
"sig_full": " ".join(sig_tokens),
"error": "no unique prefix found within collected bytes",
"status": "failed"
}))
"""
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.
- 10d ago First seen · 189 lines · 66 tokens per session scan A 84777ce14f38
generate-signature-for-function is a skill published in the GitHub repository HLND2T/CS2_VibeSignatures (65 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 1,771 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.