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.
git clone --depth 1 https://github.com/olddonkey/olddonkey-skillsWrote 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/plugins/olddonkey/olddonkey-skills/cursor-implementation-loop)<a href="https://agentmods.dev/plugins/olddonkey/olddonkey-skills/cursor-implementation-loop"><img src="https://agentmods.dev/badge/plugins/olddonkey/olddonkey-skills/cursor-implementation-loop/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/plugins/olddonkey/olddonkey-skills/cursor-implementation-loop"><img src="https://agentmods.dev/badge/plugins/olddonkey/olddonkey-skills/cursor-implementation-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cursor-implementation-loop 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 18d 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.
What it actually says
{
"name": "cursor-implementation-loop",
"description": "Review-gated implementation loop for Cursor: an implementer subagent writes code; the parent agent owns judgment, the full test gate, and publication. Ships two skills: the plan-first cursor-implementation-loop and the goal-first cursor-engineering-mode wrapper.",
"version": "0.3.0",
"author": {
"name": "olddonkey"
},
"keywords": [
"workflow",
"delegation",
"code-review",
"testing",
"subagents",
"engineering-mode"
]
}
What it installs
The manifest is a name and a version. 2 skills, 2 agents travel with it, and installing the plugin installs all of them — 410 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 18d ago First seen · 17 lines scan A ed4bbf5d7656
cursor-implementation-loop is a plugin published in the GitHub repository olddonkey/olddonkey-skills (17 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-29.
Other plugins, from other repositories
sextant
Architecture-aware engineering principles framework for Claude Code. Provides systematic, tiered workflows for bug fixes, new features, refactoring, code review, test writing, requirements refinement, debugging, shipping, sprint planning, migrations, and security audits.
quality-assurance-suite
Find gaps that could break a release, mislead a maintainer, or make a passing test meaningless.
mattpocock-skills
Skills adapted from Matt Pocock's public collection.
xonovex-core
Apply software design, testing, review, version control, credentials, and accessibility practices.
atlas-review
Takes the open pull requests of the Atlas/Bella monorepo from arrival to reviewed, fixed, merged, pushed and reported. The review itself is code-review:code-review, which is read-only, so resolving what it finds is this skill's own stage and the reason it exists. Lands by rebase rather than merge commit, pulls so…
pr-swarm
Multi-agent PR review swarm and review-triage skills.