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 softspark/ai-toolkit --skill personagit clone --depth 1 https://github.com/softspark/ai-toolkitWrote 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/softspark/ai-toolkit/persona)<a href="https://agentmods.dev/skills/softspark/ai-toolkit/persona"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/persona/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/softspark/ai-toolkit/persona"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/persona.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.01099 |
| Opus 5.5 | $0.00013 | $0.00440 |
| Sonnet 5.5 | $0.00006 | $0.00220 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
persona 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/persona - Runtime Persona Switching
$ARGUMENTS
Switch your working persona without re-installing. Personas adjust communication style, preferred skills, and code review priorities for the current session.
Usage
/persona backend-lead # Activate backend lead persona
/persona frontend-lead # Activate frontend lead persona
/persona devops-eng # Activate DevOps engineer persona
/persona junior-dev # Activate junior developer persona
/persona --list # Show available personas
/persona --clear # Reset to default (no persona)
Available Personas
| Persona | Focus | Preferred Skills |
|---|---|---|
backend-lead |
System design, scalability, data integrity, API stability | /workflow backend-feature, /tdd |
frontend-lead |
Component architecture, a11y, state management, Core Web Vitals | /design-an-interface, /review |
devops-eng |
IaC, CI/CD, blast radius, rollback safety, observability | /workflow infrastructure-change, /deploy |
junior-dev |
Step-by-step explanations, learning resources, small PRs | /explain, /explore, /debug |
Steps
- Parse
$ARGUMENTS - If
--list: read allapp/personas/*.mdfiles via Glob, display table with name and first-line summary - If
--clear: respond with "Persona cleared. Using default behavior for the rest of this session." - If persona name given:
a. Read the persona file from
app/personas/{name}.md(relative to toolkit root) b. If file not found, try the installed location:~/.claude/skills/persona/../../../app/personas/{name}.mdc. Display the persona content to Claude d. State: "Persona active: {name}. I will follow these guidelines for the rest of this session." - If no argument: show usage and available personas
How It Works
Unlike --persona at install time (which injects into CLAUDE.md permanently), /persona applies for the current session only. The persona file content is loaded into the conversation context and Claude follows it until the session ends or /persona --clear is called.
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 · 75 lines · 32 tokens per session scan A 0b5656f7dabf
persona is a skill published in the GitHub repository softspark/ai-toolkit (180 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 1,099 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 2026-09-03.
Other skills, from other repositories
cline-fix-volatile-msg
Ladder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune TTL. Updated for the 2026-08 AI-SDK monorepo.
continue-gemini-explicit
Continue's Gemini provider doesn't use the cachedContents API at all. Add explicit caching for sessions over the minimum token threshold.
roo-fix-volatile-msg
Ladder-aware Roo Code Anthropic caching — verify the rolling read/write ladder on the wire, then close the real gaps (Vertex 4-block budget, MiniMax path).
aider-1h-ttl
Aider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.
cline-openai-cache-key
Cline OpenAI native provider sends no promptcachekey. Add a stable per-task key so cachedtokens stops being zero.
continue-enable-defaults
Continue's prompt caching is opt-in via config and off by default. Flip the default to systemAndTools.