agentmods.dev

mspm0-ccs

mspm0-ccs is a skill for Claude Code, Codex from Ibook000/ibook-skill. It costs 101 tokens per session (3,700 once invoked), scanned A, original, MIT.

A set of rules for developing firmware for Texas Instruments MSPM0 microcontrollers using tools such as Code Composer Studio, Keil, CMake, and OpenOCD.

In plain words
What is it for?
Use it to inspect or modify MSPM0 projects, review SysConfig settings, update application code, and validate generated configuration and build files.
Why use it?
It helps an AI coding assistant understand the project configuration, avoid editing generated files, and use the existing SysConfig and DriverLib setup correctly. Firmware is software that runs directly on hardware.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: mentions Claude Code; mentions Codex; built for openclaw.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/ccs_dss_debug.py <project-dir> probe --leave-running.

not rated 7repo +1 2mo ago A scan 101 tokens original MIT

Good fit Use it to inspect or modify MSPM0 projects, review SysConfig settings, update application code, and validate generated configuration and build files.

Compare 6 skills from other repositories ↓
View source ↗ Ibook000/ibook-skill
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Ibook000/ibook-skill
agentmods
npx agentmods add skills/ibook000/ibook-skill/msp0-skill

Made for: Claude Code, Codex.

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.

agentmods badge for mspm0-ccs

README.md
[![agentmods](https://agentmods.dev/badge/skills/ibook000/ibook-skill/msp0-skill/github.svg)](https://agentmods.dev/skills/ibook000/ibook-skill/msp0-skill)
Your own site
<a href="https://agentmods.dev/skills/ibook000/ibook-skill/msp0-skill"><img src="https://agentmods.dev/badge/skills/ibook000/ibook-skill/msp0-skill/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.

agentmods 80×15 button for mspm0-ccs

Your own site · 80×15
<a href="https://agentmods.dev/skills/ibook000/ibook-skill/msp0-skill"><img src="https://agentmods.dev/badge/skills/ibook000/ibook-skill/msp0-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,700 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00101 $0.03700
Opus 5.5 $0.00040 $0.01480
Sonnet 5.5 $0.00020 $0.00740
Haiku 4.5 $0.00010 $0.00370

Measured 2mo ago against content hash d9d165438821, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mspm0-ccs 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 2mo 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.

skills/msp0-skill/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MSPM0 Agent Skill

Use this skill for TI MSPM0 firmware projects that use SysConfig and DriverLib through CCS / CCS Theia, Keil/uVision, or CMake + Arm GNU Toolchain + OpenOCD workflows. It is intended for Claude Code, OpenCode, OpenClaw, Continue, Cursor, Codex, and similar CLI/editor agents.

Default Workflow

  1. Locate the project .syscfg or system.syscfg, editable source files, generated ti_msp_dl_config.h, and the active project entrypoint: targetConfigs/*.ccxml for CCS, *.uvprojx plus scatter file for Keil/uVision, or CMakeLists.txt plus OpenOCD .cfg files for CMake/GCC/OpenOCD.
  2. Run python scripts/check_syscfg.py <project-dir> when this skill is available.
  3. Read .syscfg metadata: device, package, SDK product, SysConfig version, modules, instances, pins, clocks, and interrupts.
  4. Inspect generated ti_msp_dl_config.h for macro names, IRQ names, instance names, and the exact SysConfig init function spelling.
  5. Before adding unfamiliar SysConfig fields, inspect the user's existing .syscfg, examples/*/manifest.json, TI SDK examples, or source/ti/driverlib/.meta/*.syscfg.js.
  6. Modify the smallest relevant .syscfg and application-code surface.
  7. Regenerate SysConfig output or rebuild through the active toolchain's generated build flow.
  8. If flashing or debugging, confirm the configured probe backend matches the connected hardware and prefer a System Reset after programming.

Core Rules

  • Treat .syscfg as the source of truth for pinmux, peripheral setup, clocks, interrupts, DMA ownership, and generated initialization.
  • Prefer SysConfig + DriverLib for GPIO, UART, PWM, Timer, ADC, I2C, SPI, DMA, and clock setup.
  • Do not hand-edit generated outputs such as Debug/ti_msp_dl_config.c, Debug/ti_msp_dl_config.h, the project-root ti_msp_dl_config.c / ti_msp_dl_config.h pair in Keil layouts, device_linker.cmd, Objects/, Listings/, object files, maps, or .out files.
  • Preserve .syscfg metadata such as @cliArgs, @v2CliArgs, @versions, --device, --package, and --product.
  • Do not guess generated names. Read ti_msp_dl_config.h and use the local macros and the local init function spelling, such as SYSCFG_DL_init().
  • Do not invent SysConfig fields, enum values, device metadata, board names, package names, or tool versions. Validate against local examples, SDK metadata, or SysConfig CLI.
  • Preserve unrelated user code, comments, copyright headers, project layout, and existing .syscfg settings. If a requested feature requires a larger rewrite, explain why before making it when possible.
  • Do not change device, package, SDK, compiler, CCS version, board, or debug probe without user confirmation.
  • If SysConfig emits warnings, report them separately from build/flash success. Do not call a warning-producing generation "clean".
  • If hardware behavior is not verified on a connected board, say that validation stopped at source, SysConfig, or build level.

Read the full file on GitHub · 195 lines

Files

What ships with it

60 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.

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.

  1. 2mo ago First seen · 195 lines · 101 tokens per session scan A d9d165438821

Subscribe to this mod's changes

mspm0-ccs is a skill published in the GitHub repository Ibook000/ibook-skill (7 stars, last pushed 2mo ago), licensed MIT. It adds 101 tokens to every session and 3,700 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 2026-08-31.

Hardware and IoTai-agentautomationembeddedskillsworkflow
Related

mspm0-ccs compared with skills from other repositories

mspm0-ccs next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mspm0-ccsIbook000/ibook-skillSkill72mo agoMITA101Claude Code, Codex
mspm0-ccsmc3545dada/mspm0-skillSkill3783mo agoMITA101Claude Code, Codex
freecad-scriptsboshi-xixixi/TraeSkillSkill2825mo agoMITA85Claude Code, Codex
legacy-circuit-mockupsboshi-xixixi/TraeSkillSkill2825mo agoMITA111Claude Code, Codex
memory-mergerboshi-xixixi/TraeSkillSkill2825mo agoMITA49Claude Code, Codex
arduino-azure-iot-edge-integrationboshi-xixixi/TraeSkillSkill2825mo agoMITA40Claude Code, Codex
azure-smart-city-iot-solution-builderboshi-xixixi/TraeSkillSkill2825mo agoMITA43Claude Code, Codex