copilot-session-tools: Skill for Claude Code

.claude/skills/search-copilot-chats/SKILL.md

search-copilot-chats is a skill for Claude Code from Arithmomaniac/copilot-session-tools. It costs 144 tokens per session (2,938 once invoked), scanned A, original, MIT.

A search tool for archived GitHub Copilot conversations from Visual Studio Code and the Copilot command-line tool. It can find, inspect, and export earlier sessions using their local search database.

In plain words
What is it for?
Use it to search chat history, find sessions by topic or identifier, inspect a session, or export a conversation as Markdown, HTML, or JSON.
Why use it?
It avoids manually opening old conversations when you need to recover a past decision, code example, or troubleshooting discussion.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Arithmomaniac/copilot-session-tools's own configuration. It tells Claude Code how to work on copilot-session-tools 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 copilot-session-tools configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Arithmomaniac/copilot-session-tools. 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/Arithmomaniac/copilot-session-tools/main/.claude/skills/search-copilot-chats/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Arithmomaniac/copilot-session-tools

Made for: Claude Code.

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 search-copilot-chats

README.md
[![agentmods](https://agentmods.dev/badge/skills/arithmomaniac/copilot-session-tools/search-copilot-chats/github.svg)](https://agentmods.dev/skills/arithmomaniac/copilot-session-tools/search-copilot-chats)
Your own site
<a href="https://agentmods.dev/skills/arithmomaniac/copilot-session-tools/search-copilot-chats"><img src="https://agentmods.dev/badge/skills/arithmomaniac/copilot-session-tools/search-copilot-chats/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.

agentmods 80×15 button for search-copilot-chats

Your own site · 80×15
<a href="https://agentmods.dev/skills/arithmomaniac/copilot-session-tools/search-copilot-chats"><img src="https://agentmods.dev/badge/skills/arithmomaniac/copilot-session-tools/search-copilot-chats.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,938 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.
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 $0.00144 $0.02938
Opus 5.5 $0.00058 $0.01175
Sonnet 5.5 $0.00029 $0.00588
Haiku 4.5 $0.00014 $0.00294

Measured 7d ago against content hash a0d79c4ee46d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

search-copilot-chats 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 7d 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.

.claude/skills/search-copilot-chats/SKILL.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Search Copilot Chats

Search, browse, and export archived GitHub Copilot chat sessions from VS Code (Stable & Insiders) and the Copilot CLI. Use Chronicle/session_store SQL as the first hint/index layer when available, then use the copilot-session-tools CLI for targeted lookup, export, and web viewing. The CLI is backed by a local SQLite database with FTS5 full-text search. Requires Copilot CLI v0.0.412+ (uv tool install copilot-session-tools[all] if not on PATH).

Do not memorize flags. Run copilot-session-tools <command> --help for flags and examples. This skill only documents domain knowledge that --help cannot teach.

When to use

  • User asks to search past Copilot conversations ("what did we discuss about X?")
  • User supplies a session-state path or session GUID and wants archived conversation context
  • User pastes a web viewer URL like http://127.0.0.1:5000/session/{uuid}
  • User wants to find prior decisions, code patterns, or troubleshooting steps from past sessions
  • User asks to export a session as markdown, HTML, or JSON

An ordinary artifact under session-state/files is not a conversation-history request. For example, "copy the HTML report to OneDrive" uses file-transfer tools, not this skill, even if the report's path contains a session GUID.

Default workflow: Chronicle first, CLI second

For timeline, "find the session where...", prior-discussion, and session-reference tasks, start with Chronicle/session_store SQL. Treat it as the cheap hint/index layer that identifies likely sessions before running heavier CLI searches or exports.

  1. Query session_store first using the built-in SQL tool when available. Search sessions, turns, checkpoints, session_files, session_refs, and search_index for candidate session IDs, dates, branches, files, or PR/issue refs.
  2. Use query expansion yourself: search several related keywords in SQL (bug OR fix OR error, auth OR login OR token, etc.) rather than firing many broad CLI searches.
  3. Run copilot-session-tools search only after SQL hints identify likely terms, workspaces, date ranges, or session IDs. Keep it targeted.
  4. Export full markdown only after narrowing to a specific candidate session ID.

Read the full file on GitHub · 203 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. 7d ago Changed · +2 lines · +28 tokens per session a0d79c4ee46d
  2. 27d ago First seen · 201 lines · 116 tokens per session scan A 30532db815ba

Subscribe to this mod's changes

search-copilot-chats is a skill published in the GitHub repository Arithmomaniac/copilot-session-tools (14 stars, last pushed today), licensed MIT. It adds 144 tokens to every session and 2,938 once invoked, about $0.0006 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 2026-10-02.