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 patforna/auto-tasknpx agentmods add plugins/patforna/auto-task/marketplacegit clone --depth 1 https://github.com/patforna/auto-taskGrade A, and why
auto-task 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": "auto-task",
"owner": {
"name": "Patric Fornasier"
},
"metadata": {
"description": "An opinionated set of AI-agent skills to automate a large slice of the software development lifecycle including planning, implementation, review, and shipping.",
"version": "0.1.0"
},
"plugins": [
{
"name": "at",
"source": "./",
"description": "An opinionated set of AI-agent skills to automate a large slice of the software development lifecycle including planning, implementation, review, and shipping."
}
]
}
What ships with it
1 file beside marketplace.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 · 18 lines scan A 94846d799c3b
auto-task is a plugin published in the GitHub repository patforna/auto-task (3 stars, last pushed 13d 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
alfred-dev
Plugin de ingeniería de software: 8 agentes de núcleo, Selina si hay frontend y Lucius bajo demanda. Memoria persistente por proyecto, quality gates y flujos desde la idea hasta la entrega.
sdlc-graph-engineering
Turn any multi-step process into a guarded graph a machine can actually execute — typed nodes, total exit guards, bounded retry loops, durable run state, and a ledger of every step that could not run.
agentic-engineering
Spec-driven agentic engineering as graph engineering: shape (pitch) -> decide (ADR) -> execute (delegated cycle with adversarial review) -> measure -> eval, with /graph to fan work out across a fleet of subagents (diamond / router / verifier / cycle). Dark-launch eval-gated. Distilled from a real practice.
erpaval
ERPAVal — autonomous software development workflow for Claude Code. Comprehensive standalone bundle: the erpaval workflow plus 10 vendored companion skills (product-discovery, research, ultraplan, tech-stack-builder, product-strategy, working-backwards, customer-research, meta-prompt-optimizer, product-design-shared…
asdlc-tools
ASDLC suite: PRD Implementor, PR Review council, PDQC gate.
compound-selfcheck
PostToolUse soft-prompt: when a Write/Edit/MultiEdit/NotebookEdit produces > 100 LOC or > 5KB, emits a stderr reminder to ingest the change into a knowledge base (Compound Engineering, not one-shot). Audit-logs [COMPOUND-CHECK] entries to .harness/hook-trace.log for real-trigger vs performance distinction. Soft-prompt.