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 Tano73/agent-skills --skill team-kbgit clone --depth 1 https://github.com/Tano73/agent-skillsWrote 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/tano73/agent-skills/team-kb)<a href="https://agentmods.dev/skills/tano73/agent-skills/team-kb"><img src="https://agentmods.dev/badge/skills/tano73/agent-skills/team-kb/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/tano73/agent-skills/team-kb"><img src="https://agentmods.dev/badge/skills/tano73/agent-skills/team-kb.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 | $0.00133 | $0.00634 |
| Opus 5 | $0.00067 | $0.00317 |
| Sonnet 5 | $0.00027 | $0.00127 |
| Haiku 4.5 | $0.00013 | $0.00063 |
Grade A, and why
team-kb 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 10d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Knowledge Base
Answer questions by searching the team knowledge base. Never invent information — every claim must come from a retrieved document.
Step 1 — Check the local LLM wiki (if available)
If the llm-wiki-manager skill is available and a wiki/ directory exists in the workspace, query it first. It may already contain a synthesized answer.
Step 2 — Search DocMind
Call searchFlavorChunks with these parameters:
| Parameter | Value |
|---|---|
project |
Project name from the user. If unknown, call listProjects first and pick the most relevant one. |
query |
Rephrase the user's question in 3–8 keywords; expand abbreviations; add synonyms. |
mode |
"hybrid" (default). Use "fulltext" for exact terms or IDs. |
adjacentChunks |
1 or 2 when a chunk looks cut off or needs surrounding context. |
limit |
5–8 chunks; raise to 10 for broad topics. |
If results are poor or empty, retry in order:
- Rephrase the query with different keywords.
- Switch to
mode: "semantic". - Try a related project with
listProjects.
Step 3 — Build and format the answer
- Write only what the retrieved chunks support. Do not add outside knowledge.
- Cite every key point inline:
(Source: <document name>, line N)orlines N–M. - If chunks from multiple documents support the same point, cite all of them.
- For factual questions: direct answer → supporting quote → citation.
- For broad questions: use headings or bullets, each backed by a citation.
- End every response with a Sources section listing all document names used.
When information is insufficient
If no search attempt returns enough content, do not guess. Ask the user:
"Non ho trovato informazioni sufficienti nella knowledge base. Vuoi che estenda la ricerca a:
- 🌐 Web (ricerca pubblica online)?
- 🧠 Base di conoscenza interna (conoscenza generale del modello)?
In entrambi i casi indicherò sempre le fonti utilizzate."
What ships with it
1 file beside SKILL.md 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.
- 10d ago First seen · 49 lines · 133 tokens per session scan A 1c4e948719d5
team-kb is a skill published in the GitHub repository Tano73/agent-skills (2 stars, last pushed 7d ago), licensed MIT. It adds 133 tokens to every session and 634 once invoked, about $0.0007 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 2026-08-31.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…