umbra-trust-review

umbra-trust-review is a skill for Claude Code, Codex from elberacasa/umbra. It costs 60 tokens per session (942 once invoked), scanned A, original, MIT.

Instructions for reviewing AI-generated code with Umbra before shipping. Umbra gives a 0–100 trust score and reports evidence such as file and line locations for security and code-quality problems.

In plain words
What is it for?
Use them to scan repositories, apply safe automatic fixes, inspect remaining findings, and re-scan until the review is acceptable.
Why use it?
They turn code review into a required check and identify findings that should be fixed before committing or opening a pull request.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use them to scan repositories, apply safe automatic fixes, inspect remaining findings, and re-scan until the review is acceptable.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/elberacasa/umbra/umbra-trust-review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add elberacasa/umbra --skill umbra-trust-review
Clone the repo
git clone --depth 1 https://github.com/elberacasa/umbra

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for umbra-trust-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/elberacasa/umbra/umbra-trust-review/github.svg)](https://agentmods.dev/skills/elberacasa/umbra/umbra-trust-review)
Your own site
<a href="https://agentmods.dev/skills/elberacasa/umbra/umbra-trust-review"><img src="https://agentmods.dev/badge/skills/elberacasa/umbra/umbra-trust-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for umbra-trust-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/elberacasa/umbra/umbra-trust-review"><img src="https://agentmods.dev/badge/skills/elberacasa/umbra/umbra-trust-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 942 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.00942
Opus 5 $0.00030 $0.00471
Sonnet 5 $0.00012 $0.00188
Haiku 4.5 $0.00006 $0.00094

Measured 12d ago against content hash fbfb23ed5540, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

umbra-trust-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/umbra-trust-review/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Umbra Trust Review

You wrote this code. Prove it deserves to ship.

Umbra scores a repo 0–100 on two axes: SAFE (secrets, injection sinks, missing authz, hallucinated deps) and CLEAN (dead code, unused deps, mega-files, copy-paste). Every finding has file:line evidence and a confidence level. Only high/medium confidence findings affect the score.

The rule

Before you commit, open a PR, or declare a task finished:

  1. Run the scan:

    npx @elberacasa/umbra .   # or: node /path/to/umbra/dist/cli.js .
    

    Use --offline if the network is restricted, --json if you want to parse the report.

  2. Exit code 1 (score < 50) means you are not done. Do not commit. Do not rationalize. Fix the findings.

  3. Let the tool heal first: run npx @elberacasa/umbra . --fix. It applies the provably-safe fixes (unused deps, secret extraction to env vars) and re-scans. Then work the remaining manual list.

  4. Fix SAFE findings first, then CLEAN. A leaked secret is a breach; dead code is a smell. Order your work accordingly.

  5. For every finding, read the file:line evidence and fix the root cause. Never suppress, delete, or work around the check to raise the score — the score is the point.

  6. Re-run the scan after every fix round. Loop until the scan passes.

  7. If a finding is genuinely a false positive, leave the code alone and state, in one sentence with the evidence, why it is a false positive. Then continue. Low-confidence notes never block.

When Umbra blocks a write

If umbra protect hooks are installed, Umbra reviews every file you write before it lands. When a write is refused, the hook exits 2 and the stderr starts with UMBRA BLOCKED followed by the rule id and the reason.

Treat UMBRA BLOCKED as a hard stop:

  1. Read the stderr reason. It names the rule and the fix.
  2. Fix the root cause and write again (e.g. move the secret to an environment variable reference, drop the live key, choose a path outside .git/hooks).
  3. If the block is genuinely a false positive, state why in one sentence with the evidence and ask the user how to proceed. Do not silently work around it.

Read the full file on GitHub · 90 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 90 lines · 60 tokens per session scan A fbfb23ed5540

Subscribe to this mod's changes

umbra-trust-review is a skill published in the GitHub repository elberacasa/umbra (0 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 942 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.