Jev Review

What it does

When your agent uses it

• Agent Workflows work in your project

Example prompts

• “/jev-review”

Workflow steps

10 steps, taken from the first numbered list in SKILL.md.

1. 1Understand the user's requirements, invariants, and repository conventions.
2. 2Implement a coherent slice and run the relevant tests or checks.
3. 3Call jev_review to establish or refresh the baseline.
4. 4Identify the weakest important metrics, prioritizing correctness, cognitive complexity, changeability, coupling, modularity, abstraction…
5. 5Inspect the code and form a concrete hypothesis for what is lowering one or more scores.
6. 6Make the smallest justified improvement that addresses that hypothesis. Do not ask Jev to write or explain the fix.
7. 7Run relevant validation again.
8. 8Call jev_review again with the updated implementation and the prior response in previousEvaluation.
9. 9Check whether targeted scores improved and whether any other dimension regressed.
10. 10Repeat when an important weak metric remains and another evidence-based improvement is available.

What it can do on your machine

Read from SKILL.md and the folder at commit 57690af. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Jev Review loads about 1.4k tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 637 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~83

When it runs · the whole SKILL.md, loaded when a task matches

~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from NiazMorshed2007/jev-review at commit 57690af, republished under its MIT licence (© NiazMorshed2007). 637 words, ~1,358 tokens.

name

jev-review

description

Run Jev Review as a repeated scalar feedback loop during nontrivial coding work. Establish a score baseline after a coherent implementation, diagnose weak dimensions yourself, improve the code, validate it, and rescore with the previous evaluation until important metrics improve or no further justified change remains.

implement → validate → score → inspect → form a hypothesis → improve → validate → rescore

{
  "task": "The requested behavior and acceptance constraints",
  "diff": "The current implementation diff after the latest changes",
  "files": [
    {
      "path": "src/example.ts",
      "content": "Only include surrounding code needed to judge the change"
    }
  ],
  "repositoryContext": "Relevant conventions, invariants, and validation results",
  "previousEvaluation": {}
}

© NiazMorshed2007, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/jev-review of NiazMorshed2007/jev-review.

Open the folder on GitHubat commit 57690af