Borrowing it
Nothing to install: this file belongs to ricardoquesada/regenerator2000. 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/ricardoquesada/regenerator2000/main/.agent/skills/r2000-analyze-routine/SKILL.mdgit clone --depth 1 https://github.com/ricardoquesada/regenerator2000Wrote 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/ricardoquesada/regenerator2000/r2000-analyze-routine)<a href="https://agentmods.dev/skills/ricardoquesada/regenerator2000/r2000-analyze-routine"><img src="https://agentmods.dev/badge/skills/ricardoquesada/regenerator2000/r2000-analyze-routine/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/ricardoquesada/regenerator2000/r2000-analyze-routine"><img src="https://agentmods.dev/badge/skills/ricardoquesada/regenerator2000/r2000-analyze-routine.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 | $0.00036 | $0.02235 |
| Opus 5 | $0.00018 | $0.01118 |
| Sonnet 5 | $0.00007 | $0.00447 |
| Haiku 4.5 | $0.00004 | $0.00224 |
Grade A, and why
r2000-analyze-routine 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Routine Workflow
Use this skill when the user asks to "analyze this routine" or "what does this function do?"
1. Determine System & Context
- Use
r2000_get_binary_infoto get the system, filename, description, andmay_contain_undocumented_opcodeshint. - CRITICAL: The
systemfield tells you the target computer (e.g., Commodore 64, VIC-20). You MUST become an expert in that specific target computer's memory map, hardware registers, and KERNAL routines. - CONTEXT: The
filenameanddescriptiontell you the specific software being analyzed. Use this to identify standard libraries (e.g., "Hubbard music driver", "Exomizer decompressor") and to understand the likely purpose of routines based on the game's genre (e.g., "check_collision" in a shooter). - UNDOCUMENTED OPCODES: If
may_contain_undocumented_opcodesistrue, expect illegal/undocumented MOS 6502 opcodes (e.g.,LAX,SAX,SLO,DCP,ISC) within routines. These are valid instructions — do not treat them as disassembly errors.
2. Identify the Bounds
- If the user provides an address, start there.
- If no address is given, call
r2000_get_disassembly_cursorfirst — the routine starts at the cursor address. - Look for the start (entry point or label) and end (
RTS,JMP, orRTI) of the routine. - Note: Some routines end with a
JMPto a shared epilogue — that still marks the end of this routine's body. Others fall through into the next routine with no explicit return; use cross-references and logic flow to determine the boundary.
3. Read the Code
- Use
r2000_read_region(with"view": "disasm") to get the instructions. - Analyze the flow:
- Does it loop?
- Does it call other known routines or OS entry points?
- Does it access hardware registers?
- Look for common routine patterns (generic 6502):
SEI/CLIbracketing → IRQ setup/teardown.- Loop with
LDA/STAandDEX/DEY/BNE→ Memory copy or fill. - Bit-shifting,
ADC/SBCchains → Math or decompressor. - Reads a memory-mapped I/O address then branches → Hardware polling.
- Use your knowledge of the target system (from
r2000_get_binary_info) to recognize system-specific patterns:- Calls to OS/KERNAL entry points → System service calls.
- Reads/writes to hardware register addresses → I/O, video, sound, or input handling.
- Writes to interrupt vector locations → IRQ/NMI setup.
- Writes to sound chip registers → Music/SFX driver tick.
- Reads input port registers → Joystick, keyboard, or controller polling.
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 · 127 lines · 36 tokens per session scan A 6fd26337de42
r2000-analyze-routine is a skill published in the GitHub repository ricardoquesada/regenerator2000 (164 stars, last pushed 16d ago), licensed Apache-2.0. It adds 36 tokens to every session and 2,235 once invoked, about $0.0002 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
cartridge-programming
Use when writing, building, or debugging a Commodore 64 cartridge — plain 8K/16K/Ultimax or bank-switched EasyFlash — with the c64 CLI or the c64-tools MCP server. Covers the two boot mechanisms (CBM80 vs the $FFFC reset vector), the memory modes, cart-native code in ROM, the EasyFlash banking discipline from…
6502-debugging
Use when a C64 program misbehaves at runtime — crashes, corruption, wrong values, dead input, visual glitches — and you need a procedure, not a guess. Symptom-indexed playbook of runtime debugging procedures using c64-tools.
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-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.…