analyze-chat-session

analyze-chat-session is a skill for Claude Code from arc-mcp/arc-1. It costs 74 tokens per session (3,527 once invoked), scanned A, original, MIT.

A workflow for reviewing a conversation’s tool calls, results, errors, and overall approach to using MCP tools.

In plain words
What is it for?
Use it to produce feedback on a debugging or research session and identify better tool choices, prompts, and workflows.
Why use it?
It shows where tool use or instructions could be improved, while requiring sensitive information to be removed before sharing the report.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the arc-1 plugin — 24 skills, 8 commands, 1 MCP server shipped together

Good fit Use it to produce feedback on a debugging or research session and identify better tool choices, prompts, and workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arc-mcp/arc-1/analyze-chat-session
Install

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.

Any agent
npx skills add arc-mcp/arc-1 --skill analyze-chat-session
Clone the repo
git clone --depth 1 https://github.com/arc-mcp/arc-1

Made for: Claude Code.

Or install arc-1, the plugin that ships this one along with the rest of its 24 skills, 8 commands, 1 MCP server.

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 analyze-chat-session

README.md
[![agentmods](https://agentmods.dev/badge/skills/arc-mcp/arc-1/analyze-chat-session.svg)](https://agentmods.dev/skills/arc-mcp/arc-1/analyze-chat-session)
Your own site
<a href="https://agentmods.dev/skills/arc-mcp/arc-1/analyze-chat-session"><img src="https://agentmods.dev/badge/skills/arc-mcp/arc-1/analyze-chat-session.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,527 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: 1 finding, 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 Data Exfiltration · line 53
    Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.
    Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
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 $0.00074 $0.03527
Opus 5 $0.00037 $0.01764
Sonnet 5 $0.00015 $0.00705
Haiku 4.5 $0.00007 $0.00353

Measured 8d ago against content hash c1facbe7d72c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

analyze-chat-session 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.

skills/analyze-chat-session/SKILL.md · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze Chat Session

Analyze the current conversation's tool calls, responses, errors, and overall approach to produce a structured feedback report. The goal is continuous improvement of MCP tool usage patterns, prompt strategies, and ARC-1 server capabilities.

This skill is introspective — the LLM analyzes its own chat session (the conversation you're currently in, or a referenced one) and generates actionable feedback.

PRIVACY NOTICE — READ FIRST

Before using this skill's output outside the current system (e.g., pasting into a GitHub issue, sharing in a chat), the user MUST review it for sensitive data.

The analysis MUST NOT contain:

  • SAP system URLs, hostnames, IP addresses, or ports
  • Usernames, passwords, API keys, tokens, or credentials
  • Client numbers, system IDs (SID), or environment identifiers
  • Real business data (customer names, order numbers, financial values, employee data)
  • File paths that reveal internal infrastructure (home directories, mount paths)
  • Transport request numbers or package names that reveal internal naming conventions
  • Any content from SAP table previews or SQL query results containing business data

The LLM must actively redact these from the output, replacing them with generic placeholders like <SAP_HOST>, <USERNAME>, <OBJECT_NAME>, <TABLE_DATA_REDACTED>, etc.

After generating the report, remind the user: "Please review this report for any remaining sensitive information before sharing it outside your organization."


Smart Defaults (apply silently, do NOT ask)

Setting Default Rationale
Output format issue (GitHub issue-ready) Most actionable format
Severity filter All levels Don't miss anything
Focus area Entire session Comprehensive analysis
Sensitive data Redact all (see Privacy Notice) Safe by default

Proceed immediately with Smart Defaults when triggered. No questions needed.

Input

The user triggers this skill at any point during (or after) a conversation. No additional input is required — the LLM analyzes the current chat context. Proceed immediately with Smart Defaults.

Read the full file on GitHub · 337 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 · 337 lines · 74 tokens per session scan A c1facbe7d72c

Subscribe to this mod's changes

analyze-chat-session is a skill published in the GitHub repository arc-mcp/arc-1 (182 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 3,527 once invoked, about $0.0004 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-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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens