@h2loop/safe-c-coding-plugin 0.3.2 → 0.3.3

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@h2loop/safe-c-coding-plugin",
-  "version": "0.3.2",
+  "version": "0.3.3",
   "description": "Safe-C coding plugin for Hydron — MISRA C:2012-aligned defensive C/C++ guidelines as an always-on skill plus a safe-c-reviewer subagent",
   "type": "module",
   "license": "UNLICENSED",

package/skills/safe-c-coding/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: safe-c-coding
-description: ALWAYS invoke this skill before writing, generating, modifying, or reviewing any C or C++ code (.c, .h, .cpp, .hpp) — no exception for one-line changes, snippets, or code that looks routine. Scope is per file, not per project or per task — do not invoke it for code in other languages (Python, JS/TS, Rust, Go, shell, build/config, etc.), even inside a project that also contains C/C++. Applies especially to embedded, automotive, medical, aerospace, or other safety-critical or resource-constrained targets where reliability, determinism, and freedom from undefined behaviour matter, but the mandatory-invocation rule applies to all C/C++ work.
+description: Invoke this skill ONLY when authoring or reviewing C or C++ source — that is, when you are about to write, generate, or modify the contents of a .c/.h/.cpp/.hpp file, or when explicitly asked to review such source for defects. In those cases invocation is mandatory, with no exception for one-line changes, snippets, or code that looks routine. Do NOT invoke it for activities that merely involve an existing C/C++ project but do not change or review its source: flashing or programming a device, running or launching a binary, debugging a running program (setting breakpoints, inspecting variables, reading a stack trace, diagnosing a crash), building/compiling/linking, running tests, reading or explaining code without editing it, configuring toolchains, or working with logs, build output, or hardware. Reading a C/C++ file for context during such an activity is not authoring and does not trigger the skill. Scope is per file, not per project or per task — do not invoke it for code in other languages (Python, JS/TS, Rust, Go, shell, build/config, etc.), even inside a project that also contains C/C++. It applies especially to embedded, automotive, medical, aerospace, or other safety-critical or resource-constrained targets, but the trigger is always the act of writing or reviewing C/C++ source, never merely being near it.
 ---
 
 # Safe C Coding
@@ -11,6 +11,21 @@ A set of defensive coding guidelines for writing C (and C-style C++) that is rel
 
 **Core principle:** write the safe form by default. Avoid the language's hazardous corners (dynamic memory, undefined behaviour, implicit conversions, unbounded operations) instead of relying on review to catch them later.
 
+## When this skill applies
+
+The trigger is the **act of authoring or reviewing C/C++ source**, not the presence of a C/C++ project. Invoke it when you are about to write, generate, or modify the contents of a `.c/.h/.cpp/.hpp` file, or when explicitly asked to review such source for defects.
+
+Do **not** invoke it for activities that touch a C/C++ project without changing or reviewing its source:
+
+- Flashing, programming, or provisioning a device.
+- Running, launching, or deploying a binary.
+- Debugging a running program — breakpoints, inspecting variables, reading a stack trace, diagnosing a crash.
+- Building, compiling, or linking; running tests.
+- Reading or explaining existing code without editing it.
+- Configuring toolchains, or working with logs, build output, or hardware.
+
+Reading a C/C++ file for context during any of the above is not authoring and does not trigger the skill. If, during such an activity, you decide to *edit* source to fix something, the skill applies from that point.
+
 > **Apply this as you write.** Whenever you write, generate, or modify C or C++ — even a one-line snippet or a quick example — follow these MISRA C:2012-aligned guidelines proactively, without waiting to be asked to review. Produce compliant code the first time; do not emit a hazardous construct now and plan to fix it later. If a guideline genuinely cannot be met, flag it and justify the deviation rather than silently violating it.
 
 ## Non-negotiables