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.
npx agentmods add commands/atillab1/embedded-ai-workspace/misragit clone --depth 1 https://github.com/atillab1/embedded-ai-workspaceWrote 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/commands/atillab1/embedded-ai-workspace/misra)<a href="https://agentmods.dev/commands/atillab1/embedded-ai-workspace/misra"><img src="https://agentmods.dev/badge/commands/atillab1/embedded-ai-workspace/misra.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.00479 |
| Opus 5 | $0.00014 | $0.00239 |
| Sonnet 5 | $0.00005 | $0.00096 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
misra 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 6d 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.
What it actually says
Use the misra-c-reviewer skill to perform a MISRA-C:2012 (Amendment 4, 2023) review.
Input
$ARGUMENTS
How to interpret the input
Parse $ARGUMENTS as follows:
-
If it contains a file path (e.g.
main.c,src/foo.c, absolute path): Read the file and review its full contents. -
If
--strictis present: Loadreferences/rules-required.mdandreferences/rules-advisory.mdin addition torules-essential.md. Report every violation, including style-level issues. -
If
--isr-onlyis present: Skip the general MISRA review. Only run the ISR safety cross-check (volatile, race conditions, printf/malloc in ISR, reentrancy, DMA cache). -
If
$ARGUMENTSis empty or only contains flags: Ask the user to either provide a file path or paste the code they want reviewed. Don't proceed without code to review. -
If
$ARGUMENTSlooks like raw C code (contains{,;,#include, function signatures, etc.): Treat the whole argument as the code to review.
Workflow
Follow the workflow defined in the skill's SKILL.md:
- Identify scope (file vs snippet, ISR involvement, runtime context).
- Load
references/rules-essential.md(or more, if--strict). - Walk the code and report findings using the standard format:
[Rule X.Y — Mandatory/Required/Advisory] <summary>with Location, Why, and Fix sections. - Cross-check ISR safety patterns from
examples/isr-safety.c. - Summarize: counts by severity, top 3 things to fix first.
Group findings by severity (Mandatory → Required → Advisory → ISR Safety). Don't manufacture findings. If the code is clean, say so plainly.
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.
- 6d ago First seen · 50 lines · 27 tokens per session scan A c0909f6a8182
misra is a command published in the GitHub repository atillab1/embedded-ai-workspace (5 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 479 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
assemble-team
Assemble a pre-built agent team for parallel work - review, feature, debug, cross-platform, full-stack, or research.
review-pr
Multi-agent PR review with four modes (review, re-review, self-review, address-feedback) - spawns parallel subagents, saves diff to /tmp for context efficiency, supports file exclusion patterns.
check-architecture
Angular Architecture Review.
ia-agent-native-audit
Score each of the 5 agent-native principles (parity, granularity, composability, emergent capability, improvement-over-time) against a codebase and report gaps.
argos
설계 산출물 대비 구현 검증 — 준공검사 감리 (아르고스).
sm-buff
You usually don't run buff directly — run sm sail. sm sail drives the whole PR to green and calls buff watch / triage for you, stopping only when it needs you to act (see /sm-sail). Reach for sm buff here only for surgical work: inspecting a specific failure, or resolving a single review thread when sail has parked on…