Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add emaballarin/ccplugins/plugin install dm42Wrote 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/emaballarin/ccplugins/rpn)<a href="https://agentmods.dev/skills/emaballarin/ccplugins/rpn"><img src="https://agentmods.dev/badge/skills/emaballarin/ccplugins/rpn/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/emaballarin/ccplugins/rpn"><img src="https://agentmods.dev/badge/skills/emaballarin/ccplugins/rpn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00078 | $0.00948 |
| Opus 5.5 | $0.00031 | $0.00379 |
| Sonnet 5.5 | $0.00016 | $0.00190 |
| Haiku 4.5 | $0.00008 | $0.00095 |
Grade A, and why
rpn 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dm42:rpn — HP-42S-family programs, DM42n first
The program will run on a real calculator, where a silent mistake costs a reflash and a wasted run. Every step below exists so that the first run on the device is the last one: the parser drops lines without a word, stack lift turns one wrong ENTER into a plausible wrong result, and a GETKEY that halts skips the code meant to clean up.
Steps
-
Load the reference. Read
${CLAUDE_PLUGIN_ROOT}/references/rpn-semantics.mdbefore writing or reviewing a single step; also read${CLAUDE_PLUGIN_ROOT}/references/dm42n.mdwhenever the program targets a DM42/DM42n or draws (PIXEL,AGRAPH,GrMod, virtual variables). Done when you can name, for this program, every place stack lift matters, every flag and mode it changes, and every way it can stop or wait. -
Write or review the program text.
- Header comment: what it does, the devices it targets, how to run it, what it changes in the calculator and what it restores.
- One step per line, comments aligned, and the stack (
@ Y: row, X: column) after every step whose effect is not obvious. - Working variables in locals (
LSTO); flags, the angle mode andGrModsaved and restored; menu inputs validated before any computation, with anAVIEWmessage and a return to the menu on bad input; loops over integers. - Everything restorable is restored before a wait for a key; only what must follow the key comes after it.
For a review, trace the stack through every branch, loop boundary and error path, and check every rule of the reference against the code. Done when each step's stack effect is accounted for and each rule was checked, with a finding or a pass.
-
Compile with a round trip. Run
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/roundtrip.py" PROGRAM.42 PROGRAM.raw. Exit status 2 means the check could not run, and the message says why; when it is the emulator not being built for this plugin version, ask the person to run/dm42:setup, and until then compile withtxt2raw/raw2txtif installed, comparing the listing with the source step by step. Done when it printsROUND TRIP: OK. A failure names the source line the parser dropped or misread: fix that line.
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 · 29 lines · 78 tokens per session scan A 949e09067c1b
rpn is a skill published in the GitHub repository emaballarin/ccplugins (4 stars, last pushed 9d ago), licensed MIT. It adds 78 tokens to every session and 948 once invoked, about $0.0003 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 2026-10-25.
Other skills, from other repositories
telephony-and-conferencing
Runs voice and meeting infrastructure — phone systems and numbers, emergency calling obligations, conference rooms and their AV, call recording and its retention consequences, and the porting that makes provider changes go badly. Use this to replace a phone system, fix rooms nobody can start a meeting in, meet…
endpoint-management
Manages laptops, desktops and mobile devices — enrollment, configuration, patching, software distribution, and lost or compromised devices. Use this to set up device management, standardize builds, roll out software or an OS upgrade, handle a lost device, or bring an unmanaged fleet under control.
addin-operations
TIA Portal Add-In development in Visual Studio Code: creating Add-In C# projects, adding Add-In templates, compiling and debugging Add-Ins, converting Add-Ins from older TIA Portal versions and configuring Add-In project parameters.
tia-plc-operations
C# Openness implementation of PLC software engineering.
tia-sivarc
C# TIA Portal Openness V21 automation for SIMATIC Visualization Architect (SiVArc): rule tables, rules and groups, library instances, tag/text definitions, tag member settings, expression resolution, layout exchange, definition upgrade, and generation.
tia-teamcenter
TIA Portal V21 Teamcenter Gateway operations. Use for connecting to Teamcenter, searching/downloading managed projects or libraries, dataset locking, and saving projects or global libraries through the installed provider APIs.