Scan Codebase
Testing & Qualityscan-codebaseScan Codebase is an Agent Skill for testing & quality published in the Agenta-AI/agenta repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Perform a fresh-context scan of code and docs that turns verification observations and missing-test gaps into findings. Accept optional `path` and `depth` parameters and default to `path=infer`, `depth=deep`. Confirm effective variables before starting.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/Agenta-AI/agenta/blob/HEAD/agents/skills/scan-codebase/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/scan-codebase, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Scan Codebase
Read these shared references when needed:
../shared/references/findings.schema.md../shared/references/findings.lifecycle.md
Role
Run a fresh review pass from code and docs into findings.
- This skill is verification-oriented.
- It may surface missing tests or coverage gaps as findings.
- It does not rely on existing findings as the starting point.
- It does not replace
test-codebase; if runtime validation is needed, hand off there.
Depth
Accept a depth parameter from the prompt:
shallowdeep
Default:
depth=deep
Path Input
Accept an optional path from the prompt.
- If
pathis provided, use it as the local design or findings folder. - If
pathis omitted, infer it from the branch, subsystem, or matching docs and state the inferred value before starting.
Default:
path=infer
Workflow
-
Establish scan scope. Confirm the effective variables first:
pathdepth- branch, base, subsystem, and any requested focus areas
-
Start from fresh context. Read current code, docs, tests-as-code, routes, schemas, migrations, and adjacent design material before looking at existing findings.
-
Produce findings from review. Surface correctness, consistency, completeness, soundness, functionality, security, performance, compatibility, migration, and missing-test findings when supported by evidence.
-
Update the active findings record. Use
path/findings.md. -
Hand off when execution is needed. Use
triage-findingsfor discussion and planning,test-codebasefor validation, andresolve-findingsfor implementation.
Rules
- Bias toward deep inspection, not prior-thread anchoring.
- Do not silently preload old findings into the initial reasoning path.
- Do not present test execution as completed if you only inferred missing coverage from code.