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 liza-mas/liza --skill generic-subagentgit clone --depth 1 https://github.com/liza-mas/lizaWrote 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/liza-mas/liza/generic-subagent)<a href="https://agentmods.dev/skills/liza-mas/liza/generic-subagent"><img src="https://agentmods.dev/badge/skills/liza-mas/liza/generic-subagent/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/liza-mas/liza/generic-subagent"><img src="https://agentmods.dev/badge/skills/liza-mas/liza/generic-subagent.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 | $0.00022 | $0.01098 |
| Opus 5 | $0.00011 | $0.00549 |
| Sonnet 5 | $0.00004 | $0.00220 |
| Haiku 4.5 | $0.00002 | $0.00110 |
Grade A, and why
generic-subagent 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 9d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagents offload context-expensive work. The caller receives a digest, not the full trace.
Default subagents are read-only (research, analyze, summarize). READ-WRITE subagents may modify state within declared scope.
When to Delegate
See the contract's Subagent Delegation Protocol for authoritative triggers.
Summary:
| Trigger | Threshold |
|---|---|
| Uncertain scope | Assess with cheap ops first → convert to defined |
| Content to read | >250KB of files to READ (not search scope) |
| Processing depth | >2 intermediate tool calls whose outputs aren't needed in final delivery |
Clarification on 250KB:
- Applies to
Readoperations (full content enters context) - Does NOT apply to
Grep(only matches enter context) - Typical sequence: search (cheap) → identify matches → measure size of files to read → apply threshold
Keep Inline When
- Task requires user interaction mid-execution
- Result interpretation needs full conversation history
- Content to read ≤250KB and processing depth ≤2 steps
Delegation Protocol
1. Assess Scope (if uncertain)
# Check total size of files to READ (not search)
stat --printf="%s\n" src/api/*.py | awk '{sum+=$1} END {print sum}'
2. Generate Brief
MODE: SUBAGENT
MODE: SUBAGENT READ-WRITE ← only when objective requires state changes
GOAL: {{objective}}
CONTEXT: {{what caller already knows — no pre-analysis required}}
SCOPE: {{files, directories, or boundaries}}
Brief principles:
- Write from existing knowledge only — if investigation is needed to specify the goal, that IS the delegated work
- Vague goals are valid when they reflect genuine uncertainty
- Subagent has the contract — don't repeat rules in the brief
3. Dispatch
Use Task tool. Subagent inherits contract but operates in Subagent Mode (no external gates, compressed output). Default is read-only; READ-WRITE permits state modification with mandatory Intent Gate per action.
3b. Model Selection
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.
- 9d ago First seen · 137 lines · 22 tokens per session scan A 6be24137b334
generic-subagent is a skill published in the GitHub repository liza-mas/liza (372 stars, last pushed today), licensed Apache-2.0. It adds 22 tokens to every session and 1,098 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…