team-analyst: Skill for Claude Code

.agents/skills/improve-agent/SKILL.md

improve-agent is a skill for Claude Code from cas-team-analyst/team-analyst. It costs 59 tokens per session (4,814 once invoked), scanned A, original, MIT.

A guide to improving GitHub Copilot Agent’s behavior with skills, repository instructions, directory-specific rules, and AGENTS.md files.

In plain words
What is it for?
Use it to design or update Copilot skills, custom instructions, path-specific instructions, AGENTS.md files, and other repository guidance.
Why use it?
It helps place instructions where the coding agent will use them, while avoiding unnecessary context that can make agent responses less focused. It explains when each instruction type fits.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is cas-team-analyst/team-analyst's own configuration. It tells Claude Code how to work on team-analyst itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything team-analyst configures →

Part of the team-analyst plugin — 7 skills, 6 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to cas-team-analyst/team-analyst. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cas-team-analyst/team-analyst/main/.agents/skills/improve-agent/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cas-team-analyst/team-analyst

Made for: Claude Code.

Or install team-analyst, the plugin that ships this one along with the rest of its 7 skills, 6 agents.

Wrote 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.

agentmods badge for improve-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/cas-team-analyst/team-analyst/improve-agent.svg)](https://agentmods.dev/skills/cas-team-analyst/team-analyst/improve-agent)
Your own site
<a href="https://agentmods.dev/skills/cas-team-analyst/team-analyst/improve-agent"><img src="https://agentmods.dev/badge/skills/cas-team-analyst/team-analyst/improve-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,814 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 3
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • high Rogue Agent · line 563
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • medium Agent Snooping · line 13
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.04814
Opus 5 $0.00030 $0.02407
Sonnet 5 $0.00012 $0.00963
Haiku 4.5 $0.00006 $0.00481

Measured 8d ago against content hash 1befeb5e1e04, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

improve-agent 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 8d 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.

.agents/skills/improve-agent/SKILL.md · 606 lines

How it starts

The opening of the file, as written. The whole thing — 606 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Improvement Guide

Quick Reference

What this skill covers: Improving GitHub Copilot Agent performance through Skills, Custom Instructions, AGENTS.md, and path-specific instructions.

Instruction types:

  • Skills = On-demand, specialized (.github/skills/NAME/SKILL.md)
  • Custom Instructions = Always-in-context, general (.github/copilot-instructions.md)
  • Path-Specific = Context for specific files/dirs (.github/instructions/NAME.instructions.md)
  • AGENTS.md = Directory-based precedence (nearest AGENTS.md wins)

Quick decision: Need it for 80%+ of tasks? → Custom Instructions. Specific workflows only? → Skill. Different rules per directory? → Path-specific or AGENTS.md. → Decision guide

Key principles:

  • Less is more: Agents overindex on first 50 lines. Put navigation and key decisions first, details below with hash links.
  • Context is costly: Only add what Copilot doesn't already know. Challenge each piece: "Does this justify its token cost?"
  • Description triggers loading: The skill description field determines when Copilot loads it. Be specific about WHEN to use.
  • Iterate, don't perfect: Start minimal, add details based on real usage patterns. → Iteration guide
  • Match freedom to fragility: Text for flexible tasks, specific scripts for fragile operations. → Details

Setup guides:

Writing best practices:

Naming: lowercase-with-hyphens, under 64 chars, verb-led (e.g., rotate-pdf, debug-github-actions)

Read the full file on GitHub · 606 lines

Changes

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.

  1. 8d ago First seen · 606 lines · 59 tokens per session scan A 1befeb5e1e04

Subscribe to this mod's changes

improve-agent is a skill published in the GitHub repository cas-team-analyst/team-analyst (11 stars, last pushed 5d ago), licensed MIT. It adds 59 tokens to every session and 4,814 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens