misra-c-reviewer

misra-c-reviewer is a skill for Claude Code, Codex from atillab1/embedded-ai-workspace. It costs 98 tokens per session (1,445 once invoked), scanned B, original, MIT.

A guided reviewer for embedded C code, which runs on small devices, against MISRA-C:2012 guidance. MISRA-C is a set of safety-focused coding rules; the reviewer also checks interrupt-handler safety.

In plain words
What is it for?
Use it for learning MISRA rules or reviewing embedded C before formal safety work. It reports rule numbers, severity, reasons, and possible fixes.
Why use it?
It helps find important coding and firmware risks without commercial static-analysis software. It explains each finding and suggests a correction, but it is not an official certification tool.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for learning MISRA rules or reviewing embedded C before formal safety work. It reports rule numbers, severity, reasons, and possible fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/atillab1/embedded-ai-workspace/misra-c-reviewer
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.

Any agent
npx skills add atillab1/embedded-ai-workspace --skill misra-c-reviewer
Clone the repo
git clone --depth 1 https://github.com/atillab1/embedded-ai-workspace

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 misra-c-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/atillab1/embedded-ai-workspace/misra-c-reviewer/github.svg)](https://agentmods.dev/skills/atillab1/embedded-ai-workspace/misra-c-reviewer)
Your own site
<a href="https://agentmods.dev/skills/atillab1/embedded-ai-workspace/misra-c-reviewer"><img src="https://agentmods.dev/badge/skills/atillab1/embedded-ai-workspace/misra-c-reviewer/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 misra-c-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/atillab1/embedded-ai-workspace/misra-c-reviewer"><img src="https://agentmods.dev/badge/skills/atillab1/embedded-ai-workspace/misra-c-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,445 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00098 $0.01445
Opus 5 $0.00049 $0.00723
Sonnet 5 $0.00020 $0.00289
Haiku 4.5 $0.00010 $0.00145

Measured 11d ago against content hash addcaba27ce3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

misra-c-reviewer scanned grade B with 1 finding 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- **Don't lecture.** If the user pastes code, review it. Save the theory for when they ask.
misra-c-reviewer/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MISRA-C:2012 (AMD4) Reviewer

A guided code reviewer for embedded C, aimed at students and hobbyist/junior firmware developers who don't have access to commercial MISRA checkers. Catches the highest-impact rule violations and adds extra checks for ISR (Interrupt Service Routine) safety that pure MISRA does not cover.

What this skill is (and isn't)

  • Is: a structured review assistant. Loads rule summaries on demand, walks the user's code, reports violations with rule number, severity, why-it-matters, and a fix.
  • Is not: a certified MISRA tool. The official MISRA document is the source of truth for certification work. This skill is for learning and catching real bugs early, not for signing off safety-critical software.

Rule categories (quick reminder)

MISRA splits its guidance into:

  • Directives — high-level project-wide guidance (e.g. "all code shall be traceable to requirements"). Stored in references/directives.md.
  • Rules — concrete code-level checks. Each rule has a category:
    • Mandatory — must always be followed. No deviation allowed.
    • Required — must be followed unless a documented deviation exists.
    • Advisory — recommended; deviation is acceptable with judgment.

Workflow

When the user asks for a MISRA review, follow this flow. Don't railroad — adapt to what they actually need.

1. Identify scope

Ask (or infer) what the user wants reviewed:

  • A pasted snippet? A file? A whole module?
  • Bare-metal / RTOS / Linux userspace? (MISRA is strictest on bare-metal & safety-critical.)
  • Is any of it inside an ISR? (If yes, ISR safety check is required — see step 4.)

If the user is a beginner, briefly explain what MISRA is in one paragraph before diving in.

2. Load the right rule reference

Progressive disclosure — only load what you need:

  • Default first pass: load references/rules-essential.md. This covers Mandatory rules plus the highest-bug-yield Required rules (pointer conversions, type model, side effects, uninitialized vars, return-value misuse, pointer arithmetic, dynamic memory). For most student/hobbyist code this is enough.
  • If the user asks for a thorough review or the code is non-trivial: also load references/rules-required.md.
  • If the user asks about style / maintainability or wants the strictest pass: also load references/rules-advisory.md.
  • If the question is about project setup, toolchain, or process (not code): load references/directives.md.

Read the full file on GitHub · 128 lines

Files

What ships with it

8 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. 11d ago First seen · 128 lines · 98 tokens per session scan B addcaba27ce3

Subscribe to this mod's changes

misra-c-reviewer is a skill published in the GitHub repository atillab1/embedded-ai-workspace (5 stars, last pushed 4mo ago), licensed MIT. It adds 98 tokens to every session and 1,445 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.