llm-cli-gateway: Skill for Claude Code

.agents/skills/implement-review-fix/SKILL.md

implement-review-fix is a skill for Claude Code from verivus-oss/llm-cli-gateway. It costs 41 tokens per session (2,305 once invoked), scanned A, original, MIT.

A repeatable workflow for changing code, having it reviewed through the local gateway, fixing the findings, and reviewing it again. The process finishes only when required reviewers provide evidence-based unconditional approval, or when an external failure is reported.

In plain words
What is it for?
Use it for features, bug fixes, and refactoring that need implementation followed by complete local review and verification.
Why use it?
It removes the guesswork from deciding whether a change is ready. It ensures review problems are repaired and checked again instead of being left unresolved.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is verivus-oss/llm-cli-gateway's own configuration. It tells Claude Code how to work on llm-cli-gateway itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llm-cli-gateway configures →

Part of the llm-gateway plugin — 24 skills, 4 commands, 2 MCP servers shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to verivus-oss/llm-cli-gateway. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/verivus-oss/llm-cli-gateway/main/.agents/skills/implement-review-fix/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/verivus-oss/llm-cli-gateway

Made for: Claude Code.

Or install llm-gateway, the plugin that ships this one along with the rest of its 24 skills, 4 commands, 2 MCP servers.

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 implement-review-fix

README.md
[![agentmods](https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/implement-review-fix.svg)](https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/implement-review-fix)
Your own site
<a href="https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/implement-review-fix"><img src="https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/implement-review-fix.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,305 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Output Handling · line 102
    Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.
    Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
How audits are shown
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 $0.00041 $0.02305
Opus 5 $0.00020 $0.01153
Sonnet 5 $0.00008 $0.00461
Haiku 4.5 $0.00004 $0.00231

Measured 7d ago against content hash d078aaadb637, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

implement-review-fix 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 7d 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.

.agents/skills/implement-review-fix/SKILL.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement, Review, Fix

Use one parent orchestrator. It may call gateway providers, but provider jobs do not recursively orchestrate other providers. Every review dispatch uses the installed local stdio gateway MCP surface, never a direct provider binary, SDK, connector/shadow gateway, or ad hoc shell fallback.

Outcome contract

The cycle ends only after the final change set has relevant local verification and every required reviewer returns evidence-backed APPROVED_UNCONDITIONALLY. Do not use an arbitrary review-round, turn, token, price, budget, or wallclock cap. A timeout, malformed reply, residual condition, unavailable reviewer, or qualified approval is not approval.

Repair and re-review until all required reviewers approve. If a provider reaches a terminal external failure, retain the error/repair evidence and report INCOMPLETE or BLOCKED; do not silently reduce the review roster. Stop only on explicit user cancellation or after reporting the terminal blocker.

Explicit user-authorized full-access review override

Keep the ordinary implementation and inspection defaults below unless the user explicitly authorizes full provider permissions and native MCP access for the review. In that case, follow the complete multi-llm-review full-access protocol rather than weakening it into a safe-default example: build the target checkout, launch node dist/index.js --transport=stdio from that checkout, and do not use a globally installed or stale gateway process.

Apply the current provider-native full-access control on every new review job, preserve ambient provider MCP configuration without gateway tool allowlists, and do not assume a resumed session retained the grant. Give every reviewer the verification report as a corrective-program specification plus the exact base, diff or changed-file list, and persistent evidence locations. Require independent code, docs, tests, and command inspection. A report claim, intent, or green-check summary is never approval; a disputed finding needs direct code/doc/test evidence.

Read the full file on GitHub · 213 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. 7d ago First seen · 213 lines · 41 tokens per session scan A d078aaadb637

Subscribe to this mod's changes

implement-review-fix is a skill published in the GitHub repository verivus-oss/llm-cli-gateway (15 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 2,305 once invoked, about $0.0002 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 2026-08-30.