Requesting Code Review — Pre-commit review: security scan, quality gates, auto-fix
Requesting Code Review — Pre-commit review: الأمان scan, quality gates, auto-fix
Start with meaning, then move to detail.
This lesson explains Requesting Code Review — Pre-commit review: security scan, quality gates, auto-fix as part of operating Hermes with explicit security boundaries. You will learn what it does, when it matters, and the smallest safe test that proves it works.
If you are new, do not memorize names. Focus on three questions: what problem does this solve, what access does it need, and how can you verify the result?
For practice, inspect the first example, identify its effects, run it on test data, and compare the result with the source claim.
For advanced readers, inspect Skill metadata, Reference: full SKILL.md, When to Use, then verify failure modes and version compatibility.
You only need to know which files and accounts the agent may access.
A clear outcome before you read.
- Understand Requesting Code Review — Pre-commit review: security scan, quality gates, auto-fix without assumed prior knowledge.
- Separate the source description from what still needs testing in your environment.
- Read the first command and identify its inputs and outputs before copying it.
Short definitions before the details.
- Skill
- An instruction bundle that teaches Hermes a repeatable workflow without necessarily adding an external service.
- Approval & sandbox
- Approval pauses a sensitive action before execution; sandboxing limits impact if something goes wrong.
Pre-commit review: security scan, quality gates, auto-fix
What does the source say, and in what order?
- 01Skill metadata
Start here to understand the core idea or structure.
- 02Reference: full SKILL.md
Read this after the foundation, then connect it to the previous step.
- 03When to Use
Read this after the foundation, then connect it to the previous step.
- 04Step 1 — Get the diff
Read this after the foundation, then connect it to the previous step.
- 05Step 2 — Static security scan
Read this after the foundation, then connect it to the previous step.
- 06Step 3 — Baseline tests and linting
Read this after the foundation, then connect it to the previous step.
- 07Step 4 — Self-review checklist
Read this after the foundation, then connect it to the previous step.
- 08Step 5 — Independent reviewer subagent
Read this after the foundation, then connect it to the previous step.
- 09Step 6 — Evaluate results
Read this after the foundation, then connect it to the previous step.
- 10Step 7 — Auto-fix loop
Finish here to verify the result and special cases.
Copy only after you understand the effect.
git diff --cachedgit diff --name-only
git diff HEAD -- specific_file.py# Hardcoded secrets
git diff --cached | grep "^+" | grep -iE "(api_key|secret|password|token|passwd)\s*=\s*['\"][^'\"]{6,}['\"]"
# Shell injection
git diff --cached | grep "^+" | grep -E "os\.system\(|subprocess.*shell=True"
# Dangerous eval/exec
git diff --cached | grep "^+" | grep -E "\beval\(|\bexec\("
# Unsafe deserialization
git diff --cached | grep "^+" | grep -E "pickle\.loads?\("
# SQL injection (string formatting in queries)
git diff --cached | grep "^+" | grep -E "execute\(f\"|\.format\(.*SELECT|\.format\(.*INSERT"Read the first command and identify its inputs and outputs before copying it.
Match every command to your installed Hermes version, review the files and accounts it can reach, and use non-sensitive data for the first test. If this explanation differs from the source, the official source wins.