Borrowing it
Nothing to install: this file belongs to hardisgroupcom/sfdx-hardis. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hardisgroupcom/sfdx-hardis/main/.claude/skills/guinea-run/SKILL.mdgit clone --depth 1 https://github.com/hardisgroupcom/sfdx-hardisWrote 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/hardisgroupcom/sfdx-hardis/guinea-run)<a href="https://agentmods.dev/skills/hardisgroupcom/sfdx-hardis/guinea-run"><img src="https://agentmods.dev/badge/skills/hardisgroupcom/sfdx-hardis/guinea-run/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/hardisgroupcom/sfdx-hardis/guinea-run"><img src="https://agentmods.dev/badge/skills/hardisgroupcom/sfdx-hardis/guinea-run.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 | $0.00248 | $0.11262 |
| Opus 5.5 | $0.00099 | $0.04505 |
| Sonnet 5.5 | $0.00050 | $0.02252 |
| Haiku 4.5 | $0.00025 | $0.01126 |
Grade A, and why
guinea-run 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
11 files 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.
- reference/story.md 7.7 KB
- scripts/build-preview.mjs 3.0 KB runs code
- scripts/compare-portrait.mjs 1.1 KB runs code
- scripts/harness.mjs 3.6 KB runs code
- scripts/pinball-shots.mjs 3.9 KB runs code
- scripts/pinball-video.mjs 4.3 KB runs code
- scripts/pinball-video.py 2.8 KB runs code
- scripts/portrait-webp.py 796 B runs code
- scripts/preview-test.mjs 3.0 KB runs code
- scripts/preview/index.html 8.7 KB
- scripts/training-repo.mjs 561 B runs code
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.
- 3d ago Changed · +53 lines · +11 tokens per session f418e47f1b47
- 9d ago Changed · +18 lines c8fd9984c10d
- 10d ago Changed · +68 lines · +19 tokens per session 2281bfdf415b
- 14d ago Changed · +129 lines · +25 tokens per session e9e959b5fdd2
- 15d ago First seen · 305 lines · 193 tokens per session scan A 35906a5d65b5
guinea-run is a skill published in the GitHub repository hardisgroupcom/sfdx-hardis (430 stars, last pushed yesterday), licensed AGPL-3.0. It adds 248 tokens to every session and 11,262 once invoked, about $0.0010 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 2026-10-23.
guinea-run compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| guinea-runhardisgroupcom/sfdx-hardis | Skill | 430 | yesterday | AGPL-3.0 | A | 248 | Claude Code |
| blockbench-mcp-modelingsosadly/blockbench-mcp | Skill | 65 | 9d ago | MIT | A | 150 | Claude Code, Codex |
| update-readmeYoungLeadersDotTech/young-leaders-tech-marketplace | Skill | 10 | 4d ago | MIT | A | 52 | Claude Code |
| changelog-generatorglincker/claude-code-marketplace | Skill | 38 | 1mo ago | Apache-2.0 | A | 18 | Claude Code |
| tech-writerglincker/claude-code-marketplace | Skill | 38 | 1mo ago | Apache-2.0 | A | 23 | Claude Code |
| docsmartineserios/thebrana | Skill | 3 | today | MIT | A | 27 | Claude Code |
| readme-generatorglincker/claude-code-marketplace | Skill | 38 | 1mo ago | Apache-2.0 | A | 18 | Claude Code |