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.
npx skills add EdwardAF-IT/Personetta --skill personetta-listgit clone --depth 1 https://github.com/EdwardAF-IT/PersonettaWrote 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/edwardaf-it/personetta/personetta-list)<a href="https://agentmods.dev/skills/edwardaf-it/personetta/personetta-list"><img src="https://agentmods.dev/badge/skills/edwardaf-it/personetta/personetta-list/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/edwardaf-it/personetta/personetta-list"><img src="https://agentmods.dev/badge/skills/edwardaf-it/personetta/personetta-list.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 | $0.00033 | $0.00241 |
| Opus 5.5 | $0.00013 | $0.00096 |
| Sonnet 5.5 | $0.00007 | $0.00048 |
| Haiku 4.5 | $0.00003 | $0.00024 |
Grade A, and why
personetta-list 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 1mo 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
Personetta — list recipes / roles
Goal
Run personetta list so the user sees recipe ids they can pass to
set-active.
Running the CLI (no repository required)
Personetta runs from its installed CLI; you do not need a checkout. Use the first invocation that works:
personetta <args>— the installed console script.python -m generator <args>— module fallback whenpersonettais not on PATH but the package is installed.
Commands
personetta list # roles and recipes
personetta list --recipes # recipes only
You can filter with glob patterns, e.g. personetta list '*game*' 'test-*'.
Output
Recipe names are the ids to pass to personetta set-active <name> (the
format is auto-detected from the host agent).
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.
- 1mo ago First seen · 37 lines · 33 tokens per session scan A a25c95b2a430
personetta-list is a skill published in the GitHub repository EdwardAF-IT/Personetta (2 stars, last pushed 19d ago), licensed MIT. It adds 33 tokens to every session and 241 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
threnody-swarm-review
Run a complexity-gated review swarm: fans out one agent per (file × dimension) — logic, security, edge/null, types, performance — then synthesizes findings into a ranked report. Model selection per agent routed through Threnody. Use for deep parallel review, security-critical audit, threat-modeling, or explicit…
threnody-swarm
Start and run Threnody executeswarm with host-native hostspawnwaves, topology selection (dag/star/hierarchical/auto), budget preview, and resume. Use when user asks to swarm, fan out agents, or run multi-agent waves with swarmid persistence.
threnody-plan
Threnody planning mode for normal orchestration and swarms. Use when user asks to plan, decompose, show waves, dry run, preview swarm, or before multi-file work. Always confirms the wave plan before spawning any agent.
threnody-workflow
Run a Threnody swarm with multi-queen consensus and learning THROUGH the Claude Code Dynamic Workflow feature, then save the run as a permanent, pre-tuned, zero-config /workflow command for coworkers. Use when asked to run a workflow, workflow-swarm, tier-aware workflow, or to save/share a reusable multi-agent…
threnody-fast-review
Fast broad code review swarm: one read-only host agent per file, then one synthesis agent. Use when asked for a fast swarm review, one-agent-per-file review, broad review sweep, ordinary swarm review, or when reviewing many files where coverage and speed matter more than per-dimension depth.
threnody-fullstack
Build frontend, backend, and API in parallel with Threnody using contract-first DAG waves. Use for full-stack app scaffolding, OpenAPI-first development, parallel UI and service agents, or integration smoke tests after fanout.