codeguard-shell

Shell Codeguard Gate

Goal: turn "looks fine" into repeatable tool evidence, and honestly distinguish pass, fail, unable to verify, and planned.

30-second start

1. At the repository root, confirm that 无专用标记文件 or the target file exists.
2. Probe tools:shellcheck --version。
3. First do a read-only check:bash -c 'find . \( -name '"'"'*.sh'"'"' -o -name '"'"'*.bash'"'"' -o -name '"'"'*.zsh'"'"' \) -type f -not -path '"'"'*/node_modules/*'"'"' -print0 | xargs -0 shellcheck --severity=warning'。
4. Classify results into: code violations, missing configuration, missing tools, tool internal errors.
5. Only perform on safely fixable items:shfmt -w .。
6. Re-run lint, and execute the project's existing test/build gates.

Can directly propose:

• "Check this Shell project, do not modify anything first, and give me a classification of lint failures."
• "Only fix Shell formatting issues; list semantic issues first."
• "Verify Shell lint, test, and build evidence before committing."

Capability boundaries

✅ Good at handling

1. Identify the Shell workspace based on .sh, .bash, .zsh and project markers.
2. Execute shellcheck '{file}' and retain exit codes, scope, and tool versions.
3. Distinguish formatting, static rules, configuration, dependency, and environment-related failures.
4. Use shfmt -w . to handle reversible issues and re-scan.
5. Report local results and CI/build/test evidence in layers.

⚠️ Requires conditions

1. The target tool must already be installed and its version compatible with project constraints.
2. Must be executed from the correct repository or module root directory.
3. If the project has custom configuration, the committed configuration prevails.
4. Whether generated code, vendor, and cache directories are scanned must follow repository rules.

❌ Out of scope

1. Do not treat formatter passing as compilation, test, or security audit passing.
2. Do not silently install tools, upgrade dependencies, or modify team rules.
3. Do not use suppress/ignore/raising thresholds to conceal real issues.
4. Do not claim "check passed" when tools or configuration are missing.

When to use

• The user requests checking or fixing Shell code standards.
• AI modified .sh, .bash, .zsh, and pre-commit verification is needed.
• CI shows failures related to shellcheck '{file}' .
• Need to determine whether an issue can be automatically fixed or must be handled manually.

When not to use

• If the main task is learning language syntax, framework design, or business modeling, use the corresponding language professional skill instead.
• If the main task is dependency vulnerabilities, security auditing, or license governance, use a specialized security skill.
• When the user only asks to explain an error and there is no project context, first provide a local explanation and do not claim the repository is all green.

Data and security

This skill does not collect, upload, send, or store user code and credentials. By default it only reads local repository configuration and runs local tools; it does not install dependencies over the network, and does not log tokens, passwords, or private source code. Before any automatic fix, check the diff first; destructive or large-scale changes must be explicitly confirmed by the user.

Execution Contract

Item	Current Fact
Status	stable(Since Codeguard V0.2)
File Extensions	.sh, .bash, .zsh
Project Marker	No dedicated marker file
Integration Configuration	Based on the repository's existing configuration
Tool Preparation	brew install shellcheck shfmt
Probe Command	使用命令查找与项目配置检查
lint	shellcheck '{file}'
format/fix	shfmt -w .
Project-level gate	bash -c 'find . \( -name '"'"'*.sh'"'"' -o -name '"'"'*.bash'"'"' -o -name '"'"'*.zsh'"'"' \) -type f -not -path '"'"'*/node_modules/*'"'"' -print0 | xargs -0 shellcheck --severity=warning'

Standard Workflow

Step 1: Determine the Real Scope

Confirm the repository root, module roots, generated directories, vendor directories, and user-specified files. For multi-module projects, first list the modules to be scanned; do not guess based on the current directory.

Step 2: Read the Project Contract

Read the actual commands in the repository's existing configuration and CI. Repository configuration takes precedence over this skill's examples; if the two conflict, report the discrepancy first.

Step 3: Probe Tools and Versions

Run 对应工具 --version. Missing tools, incompatible versions, or configuration that cannot be loaded are all recorded as "unable to verify", not passed.

Step 4: Run Read-Only Checks

Run bash -c 'find . \( -name '"'"'*.sh'"'"' -o -name '"'"'*.bash'"'"' -o -name '"'"'*.zsh'"'"' \) -type f -not -path '"'"'*/node_modules/*'"'"' -print0 | xargs -0 shellcheck --severity=warning', recording the command, working directory, exit code, tool version, and first actionable error.

Step 5: Failure Classification

Type	Typical Signal	Handling
Format	Indentation, whitespace, import order	Formatter allowed, then check the diff
Static Rules	unused, complexity, naming, dangerous APIs	Minimal semantic fixes; no bulk guessing
Configuration	parser/config/schema not found	Fix the integration or report prerequisites
Environment	command not found, version conflicts	Report installation/version requirements; do not install silently
Tool Internal Errors	crash, timeout, parser exception	Preserve the original evidence and narrow the reproduction scope

Step 6: Controlled Fixes

Prioritize running shfmt -w .. Only handle issues that are certain and reversible; dependency upgrades, rule exemptions, generated files, and business semantic changes must be explained separately.

Step 7: Verification Loop

Re-run the same lint command, then run the project's existing tests and build. Write "passed" only when the command, scope, and exit code are all clear; otherwise write "not run" or "unable to verify".

Rules

1. Re-verify with the Same Command: after fixing, the original command that triggered the failure must be re-run.
2. Layered Evidence: report lint, format, compile, test, and security separately.
3. Minimal Changes: no incidental refactoring; do not expand a style fix into a business rewrite.
4. Configuration First: do not override the project's existing ignore, dialect, target, or version constraints.
5. No Fabrication: tools not run, configurations not seen, and platforms not verified must be explicitly marked.

Output Template

Shell Codeguard 结果
- 范围：<仓库/模块/文件>
- 工具：<名称与版本>
- 命令：<实际命令>
- 状态：PASS / FAIL / UNVERIFIED / PLANNED
- 发现：<按格式/规则/配置/环境分类>
- 修改：<文件与原因；无修改写 none>
- 复验：<命令、退出码>
- 未验证：<测试/构建/平台差异>

Gotchas

1. Missing Tools Are Not a Pass — must output UNVERIFIED and an explicit preparation method.
2. Formatter Is Not a Linter — All-green formatting cannot override static rules or compilation errors.
3. Root directory determines the result — Running in the wrong module may miss issues or load the wrong configuration.
4. Placeholders are not literal arguments — {file} must be replaced with real, authorized paths.
5. Auto-fix may expand the diff — After fixing, review the diff first, then run the regression gate.
6. Generated and vendor directories require an explicit policy — Do not arbitrarily scan or modify third-party content across the whole repository.

Domain pitfalls and fixes

1. Domain pitfall — ShellCheck must match the script shebang; the semantics of bash, sh, and zsh must not be mixed.

When information is insufficient

Do not just say "please provide more information." First give a safe read-only inspection plan, and list the specific items that still need confirmation:

1. Repository/module root directory;
2. Target tool and version;
3. Project configuration files;
4. Authoritative commands in CI;
5. Whether auto-fix is allowed.

FAQ

Q1: If the tool is not installed, can we conclude the code is fine? No. The status must be UNVERIFIED。

Q2: Can ignore or suppression be added automatically? No. Exemptions can only be granted when the user explicitly accepts them and the reason is recorded.

Q3: Why does it still fail after formatting? The formatter only covers formatting; static rules, configuration, compilation, and tests still need to be handled separately.

Q4: Should generated code be scanned? By default, follow the repository configuration; if there is no rule, first exclude generated/vendor content, then explain to the user.

Q5: How can we avoid changing too much at once? First fix in batches by failure category and file, and rerun the original command and review the diff for each batch.

Q6: If it passes locally, can we say CI will pass? No. You also need to align CI's versions, environment variables, operating system, and command scope.

Load resources on demand

• When encountering exit codes, failure classification, or exemption decisions, read references/rules/gate-rules.md。
• When you need to verify this language's registry, toolchain, and project configuration, read references/tooling/toolchain.md。
• When you need copyable task examples, read by scenario examples/, and there is no need to load all of them at once.