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.
npx skills add Netcracker/qubership-ai-packages --skill final-reviewgit clone --depth 1 https://github.com/Netcracker/qubership-ai-packagesWrote 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.
[](https://agentmods.dev/skills/netcracker/qubership-ai-packages/final-review)<a href="https://agentmods.dev/skills/netcracker/qubership-ai-packages/final-review"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/final-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.
<a href="https://agentmods.dev/skills/netcracker/qubership-ai-packages/final-review"><img src="https://agentmods.dev/badge/skills/netcracker/qubership-ai-packages/final-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00218 | $0.03098 |
| Opus 5.5 | $0.00087 | $0.01239 |
| Sonnet 5.5 | $0.00044 | $0.00620 |
| Haiku 4.5 | $0.00022 | $0.00310 |
Grade A, and why
final-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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Final review of a change
This skill is a form, not a reading. The agent that wrote a change re-reads its own text and finds nothing, because a fact it left out leaves no trace in what it wrote; a second agent with a fresh context and a fixed list of questions finds what the first could not. The list is short on purpose, and every item is answered in writing, "none" included, so that an item cannot be skipped by not noticing it.
The rules the items check belong to other skills: test-authoring for what a test establishes and how its failure
reads, the doc-comment skill of the language (javadoc-authoring and its siblings) for what a comment says, the
developer-style skill for wording. Load the two that apply to the change's language before filling the form, and
cite their sections in the findings; do not restate them here. Wording enters this form only where it makes a
sentence read wrongly, which is a finding under the first item; a pass over the prose for style alone is not this
review, and the closing sentence of the report says it was not done.
1. Inputs
- The diff: the branch against its base, or the uncommitted change. Read it whole before the form.
- The task statement: the issue, the problem description, or the prompt the change answered. It is where the claimed cases come from. Ask for it if it was not handed over; a subagent that cannot ask answers item 2 from the commit message alone and says so in the report.
- The commit message and the class comments of the tests, which claim cases too.
- The previous report of this form over the same change, where one exists. A change reviewed more than once, as in a review loop, is re-read against that report first (§4).
- The output of
scripts/comment-drift.py <base> [<head>], run from anywhere in the repository. It lists, per changed file, every member whose code or doc comment moved, named with its parameter types so that overloads stay apart and followed by its line, taggedcode-changed, comment-unchanged,comment-added,comment-changed, orcode-changed, no-comment. The first tag is the list of comments to re-read that nobody edited; the parse is approximate, so a member it misses is still yours to find.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 183 lines · 218 tokens per session scan A 937127a6b56c
final-review is a skill published in the GitHub repository Netcracker/qubership-ai-packages (4 stars, last pushed today), licensed Apache-2.0. It adds 218 tokens to every session and 3,098 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-09-10.
Other skills, from other repositories
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.