claude-sessions: Instructions file for Claude Code

CLAUDE.md

claude-sessions CLAUDE.md is an instructions file for Claude Code from gapmiss/claude-sessions. It costs 1,458 tokens per session, scanned A, original, MIT.

Development instructions for an Obsidian plugin that lets users browse, search, export, and monitor Claude Code sessions stored as JSONL files.

In plain words
What is it for?
Developing the session viewer, its JSONL parsers, settings, commands, tool rendering, tests, or build process.
Why use it?
They give a coding agent the project’s file structure, commands, parsing conventions, and testing expectations when changing the plugin.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

This is gapmiss/claude-sessions's own configuration. It tells Claude Code how to work on claude-sessions 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 claude-sessions configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gapmiss/claude-sessions. 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/gapmiss/claude-sessions/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/gapmiss/claude-sessions

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 claude-sessions CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gapmiss/claude-sessions/claude-md/github.svg)](https://agentmods.dev/instructions/gapmiss/claude-sessions/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/gapmiss/claude-sessions/claude-md"><img src="https://agentmods.dev/badge/instructions/gapmiss/claude-sessions/claude-md/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 claude-sessions CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gapmiss/claude-sessions/claude-md"><img src="https://agentmods.dev/badge/instructions/gapmiss/claude-sessions/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,458 This file is loaded in full into every session.
When invoked 1,458 The same file — it is already loaded in full.
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 $0.01458 $0.01458
Opus 5.5 $0.00583 $0.00583
Sonnet 5.5 $0.00292 $0.00292
Haiku 4.5 $0.00146 $0.00146

Measured 8d ago against content hash 8ffcafa51933, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-sessions CLAUDE.md 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.

CLAUDE.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Sessions (Obsidian plugin)

Desktop-only viewer for Claude Code JSONL sessions. Browse, search, and export sessions with rich tool rendering, live watch, and a summary dashboard.

Version: 0.3.31 | Branch: main

Development

npm run dev          # watch mode
npm run build        # typecheck + production bundle (does not copy to a vault)
npm test             # vitest
npm run test:watch   # vitest in watch mode
npx eslint .         # lint
npm run release      # bump patch, build, commit, tag, push (release:minor, release:major)

npm run release pushes to GitHub, and the tag triggers the release workflow. Don't run it unless asked.

File structure

src/
  main.ts                    # Plugin entry, commands, protocol handler
  settings.ts                # Declarative settings tab (getSettingDefinitions, 1.13.0+)
  types.ts                   # Shared interfaces, DEFAULT_SETTINGS
  constants.ts               # JSONL record types, XML tags, regexes, reviewed-and-skipped maps
  api.ts                     # Public API for other plugins
  electron.d.ts              # Minimal Electron types (save dialog)
  parsers/
    claude-parser.ts         # Core JSONL parser (record merging, dedup, stats, cost)
    claude-content.ts        # Content block parsing, tool result extraction
    claude-subagent.ts       # Sub-agent JSONL resolution
    base-parser.ts           # Abstract base (splitLines, tryParseJson)
    detect.ts                # Format detection
  views/
    timeline-view.ts         # ItemView: timeline, controls, filters, live watch
    timeline-renderer.ts     # Turn and block rendering, ANSI, mermaid, image modals
    render-helpers.ts        # Shared helpers: makeClickable, fence, stripFenceMarkers, normalizeMarkdown
    summary-renderer.ts      # Dashboard panel (hero cards, charts, metadata)
    system-events-renderer.ts # System events panel (hooks, skills, output style, permissions)
    tool-renderer.ts         # Per-tool rendering (Bash, Edit, Write, Read, WebFetch, Agent, Task*, AskUserQuestion, ToolSearch)
    search-view.ts           # Search panel (cross-session and in-session)
    session-browser-modal.ts # SuggestModal over the cached session index, with pinning
    file-picker-modal.ts     # Import by drag-and-drop or path
    export-modal.ts          # Export options (summary and system events toggles)
  exporters/
    html-exporter.ts         # DOM snapshot to standalone HTML
    css-capture.ts           # Theme, app, and plugin CSS extraction
    standalone-player.ts     # Embedded JS for exported HTML
    markdown-exporter.ts     # Markdown with frontmatter, summary, system events, tool rendering
  distill/
    distill-session.ts       # Orchestrator (extract, find, merge, write)
    extract-frontmatter.ts   # Session stats to YAML frontmatter
    serialize-frontmatter.ts # Frontmatter serialization and parsing
    build-note.ts            # Note generation and merge logic
    find-existing.ts         # Existing note lookup by session_id
    bases-templates.ts       # Obsidian Bases dashboard templates
    types.ts                 # DistilledFrontmatter, SessionType, DistillOptions
  utils/
    path-utils.ts            # expandHome, basename, dirname, shortenPath
    rate-limits.ts           # OAuth credential lookup and Anthropic usage API (beta)
    session-index.ts         # Persistent metadata cache (JSON on disk)
    session-search.ts        # Line-by-line JSONL search with BM25 ranking
    bm25.ts                  # BM25 scoring (tokenizer, stemmer, index)
    streaming-reader.ts      # File I/O (Node streams, metadata extraction)
    logger.ts                # Configurable log levels
tests/                       # Vitest suites and fixtures
skills/distill/SKILL.md      # The /distill skill for Claude Code

Read the full file on GitHub · 95 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 Changed 8ffcafa51933
  2. 20d ago Changed f1e90adf1604
  3. 27d ago Changed 0e452cd92964
  4. 28d ago Changed 8e6904fe5033
  5. 1mo ago Changed · +8 lines · +232 tokens per session 4aaa840b6d0c
  6. 1mo ago Changed · -18 lines · -272 tokens per session c389f8787094
  7. 2mo ago First seen · 105 lines · 1,498 tokens per session scan A c463400478d2

Subscribe to this mod's changes

claude-sessions CLAUDE.md is an instructions file published in the GitHub repository gapmiss/claude-sessions (6 stars, last pushed 9d ago), licensed MIT. It adds 1,458 tokens to every session, about $0.0058 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 2026-08-31.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens