codeguard-cobol

COBOL Codeguard Gate

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

Start in 30 seconds

Currently planned only means Codeguard can identify .cbl, .cob, .cpy, not that an executable gate exists.

1. Explicitly report "identified, but currently not verifiable by Codeguard".
2. Preserve the project's existing IDE, compiler, or platform diagnostic results; do not fabricate generic commands.
3. If a check is required, use the target platform's official tools and mark the results as external evidence.
4. Only after adding detection, lint, failure samples, and regression tests can the registry be upgraded to stable/beta.

Capability boundaries

✅ Good at handling

1. Identifying COBOL files and related user intent.
2. Clearly stating the current Codeguard support status and gaps.
3. Defining verifiable acceptance conditions for future integration.

⚠️ Requires conditions

1. Real target tool or platform diagnostic output.
2. At least one failure sample and one pass sample.
3. A repeatable non-interactive command or clear host boundary.

❌ Not applicable

1. Do not run nonexistent generic linter commands.
2. Do not write extension identification as a quality gate pass.
3. Do not upgrade support status without runtime evidence.

When to use

• The user requests checking or fixing COBOL code standards.
• The AI modified .cbl, .cob, .cpy, requiring pre-commit verification.
• CI shows failures related to COBOL 工具链 .
• Need to determine whether an issue can be automatically fixed or must be handled manually.

When not to use

• When the main task is learning language syntax, framework design, or business modeling, use the corresponding language professional skill instead.
• When the main task is dependency vulnerabilities, security audits, or license governance, use a dedicated security skill.
• When the user only asks to explain an error and there is no project context, provide a local explanation first 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 record tokens, passwords, or private source code. Check the diff before any automatic fix; destructive or large-scale changes must be explicitly confirmed by the user.

Execution contract

Item	Current fact
Status	planned(since Codeguard V0.5)
File extensions	.cbl, .cob, .cpy
Project marker	No dedicated marker file
Integration configuration	Subject to the repository's existing configuration
Tool readiness	No standalone CLI linter (relies on platform IDE diagnostics)
Detection command	使用命令查找与项目配置检查
lint	未接入
format/fix	未接入
Project-level gate	未接入

Standard Workflow

Step 1: Determine the true 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 repository's existing configuration as authoritative and the actual commands in CI. Repository configuration takes precedence over this skill's examples; if the two conflict, report the differences first.

Step 3: Detect tools and versions

Run 对应工具 --version. Missing tools, incompatible versions, or unloadable configuration are all recorded as "unable to verify", not as passing.

Step 4: Run read-only checks

Run 目标平台官方诊断, recording the command, working directory, exit code, tool version, and the first actionable error.

Step 5: Failure classification

Type	Typical signal	Handling
Formatting	Indentation, whitespace, import order	Formatter allowed; then check the diff
Static rules	unused, complexity, naming, dangerous APIs	Minimal semantic fix; no bulk guessing
Configuration	parser/config/schema not found	Fix the integration or report the prerequisites
Environment	command not found, version conflict	Report installation/version requirements; do not install silently
Tool internal error	crash, timeout, parser exception	Preserve the original evidence and narrow down the reproduction scope

Step 6: Controlled fixes

Prefer to run 人工最小修复. 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. Only write "passing" 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, you must re-run the original command that triggered the failure.
2. Layered evidence: Report lint, format, compile, test, and security separately.
3. Minimal changes: Do not refactor along the way, and 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 clearly marked.

Output template

COBOL 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 is not passing — must output UNVERIFIED and a clear preparation method.
2. A formatter is not a linter — all-green formatting cannot cover static rules or compilation errors.
3. The 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. Automatic fixes may expand the diff — After fixing, review the diff first, then run the regression gates.
6. Generated and vendor directories require an explicit policy — Do not arbitrarily scan or modify third-party content in full.

Domain pitfalls and fixes

1. Domain pitfalls — The current entry is marked as planned; it depends on a specific compiler/IDE, and a generic CLI must not be fabricated.

When information is insufficient

Do not just say "please provide more information." First provide 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. the authoritative command in CI;
5. whether automatic fixes are allowed.

FAQ

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

Q2: Can ignore or suppression be added automatically? No. Exemption is allowed only when the user explicitly accepts it 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 are no rules, exclude generated/vendor first, then explain to the user.

Q5: How can too many changes at once be avoided? Fix in batches by failure category and file first, and after each batch rerun the original command and review the diff.

Q6: If it passes locally, can you say CI will pass? No. The CI version, environment variables, operating system, and command scope also need to be aligned.

Load resources on demand

• When encountering exit codes, failure classification, or exemption decisions, read references/rules/gate-rules.md。
• When you need to check 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 them all at once.