SonarCloud-Skill-Agent-Guidance

SonarCloud-Skill-Agent-Guidance is an instructions file for Codex, OpenCode from Nick2bad4u/SonarCloud-Skill. It costs 435 tokens per session, scanned A, original, Unlicense.

Repository-specific instructions for maintaining a skill that manages SonarCloud or SonarQube findings. SonarCloud and SonarQube scan code for bugs, security problems, and maintainability issues.

In plain words
What is it for?
Updating the skill entrypoint, its Python command-line tool, supporting files, packaged assets, and automation while following token-handling, dry-run, review, and validation rules.
Why use it?
It keeps changes to the packaged skill focused and helps prevent security mistakes, such as exposing access tokens or closing findings without reviewing the code. It also defines how to validate the package.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/nick2bad4u/sonarcloud-skill/agents-md
Clone the repo
git clone --depth 1 https://github.com/Nick2bad4u/SonarCloud-Skill

Made for: Codex, OpenCode.

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 SonarCloud-Skill-Agent-Guidance

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nick2bad4u/sonarcloud-skill/agents-md.svg)](https://agentmods.dev/instructions/nick2bad4u/sonarcloud-skill/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/nick2bad4u/sonarcloud-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/nick2bad4u/sonarcloud-skill/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 435 This file is loaded in full into every session.
When invoked 435 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00435 $0.00435
Opus 5 $0.00217 $0.00217
Sonnet 5 $0.00087 $0.00087
Haiku 4.5 $0.00044 $0.00044

Measured 3d ago against content hash e4ef24723128, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

SonarCloud-Skill-Agent-Guidance 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 3d 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.md · 42 lines

What it actually says

SonarCloud Skill Guidance

This repository packages the sonar-manage-findings Codex/open-agent skill. Keep changes focused on the root skill payload and the small repository automation needed to publish it.

Scope

  • Treat skills/sonar-manage-findings/SKILL.md as the user-facing skill entrypoint.
  • Treat skills/sonar-manage-findings/scripts/manage_sonar_findings.py as the CLI entrypoint.
  • Keep helper modules in skills/sonar-manage-findings/scripts/ stdlib-only unless a dependency is explicitly justified and documented.
  • Keep skills/sonar-manage-findings/agents/openai.yaml, skills/sonar-manage-findings/assets/, and skills/sonar-manage-findings/LICENSE.txt synchronized with the packaged skill.

Security

  • Never put Sonar tokens in command arguments, docs examples, logs, commits, or chat output.
  • Prefer token environment variables such as SONAR_TOKEN or a caller-specified --token-env.
  • Use --dry-run first for mutating operations that affect issues, hotspots, settings, tags, quality gates, or quality profiles.
  • Do not mark findings false positive, won't fix, safe, or fixed unless the surrounding code/config has actually been reviewed.

Validation

Run the narrowest useful checks after edits:

python -m compileall skills/sonar-manage-findings/scripts
npm run release:verify

For behavior changes, also run the relevant CLI command with --json against a safe repository or use --dry-run for mutations.

Style

  • Prefer clear argparse surfaces and explicit error messages.
  • Keep API response parsing defensive; validate external JSON before indexing nested fields.
  • Keep docs examples copy-pasteable in PowerShell.
  • Avoid broad repo-template changes unless the task is explicitly about repository automation or packaging.
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. 3d ago First seen · 42 lines · 435 tokens per session scan A e4ef24723128

Subscribe to this mod's changes

SonarCloud-Skill-Agent-Guidance is an instructions file published in the GitHub repository Nick2bad4u/SonarCloud-Skill (1 stars, last pushed 11d ago), licensed Unlicense. It adds 435 tokens to every session, about $0.0022 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.