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.
/plugin marketplace add Thomaszhou22/self-discover-skillnpx agentmods add plugins/thomaszhou22/self-discover-skill/claude-plugingit clone --depth 1 https://github.com/Thomaszhou22/self-discover-skillGrade A, and why
self-discover-reasoning 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 2d 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": "self-discover-reasoning",
"version": "1.0.0",
"description": "SELF-DISCOVER: AI agents self-compose reasoning structures from seed modules.",
"author": "Thomas Zhou",
"repository": "https://github.com/Thomaszhou22/self-discover-skill",
"entry": "SKILL.md"
}
What ships with it
1 file beside plugin.json 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.
- 2d ago First seen · 9 lines scan A 6caade7ece58
self-discover-reasoning is a plugin published in the GitHub repository Thomaszhou22/self-discover-skill (3 stars, last pushed 3mo ago), 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 2026-08-31.
Other plugins, from other repositories
milestone-driver
Drives a GitHub milestone to completion: triages each issue for design gaps + dependency order up front, then for each buildable issue finds the root cause (or parks it), dispatches a TDD implementer subagent, runs unit + E2E tests + code review, opens a PR, and auto-merges issues on CI green. The whole loop sits…
finding-unknowns
Surface your unknowns (unknown unknowns / unknown knowns) before, during, and after implementation — eight lightweight techniques, Cartographer mode (a quadrant-coverage-gated, regret-weighted interview backed by a lifecycle-persistent unknowns ledger), and four companion agents: blindspot-scout, prototype-smith…
lco marketplace
Lossless Codex Orchestrator companion plugins for local recall.
supabase
Supabase MCP integration for database operations, authentication, storage, and real-time subscriptions. Manage your Supabase projects, run SQL queries, and interact with your backend directly.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.