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.
curl -O https://raw.githubusercontent.com/gapmiss/claude-sessions/main/CLAUDE.mdgit clone --depth 1 https://github.com/gapmiss/claude-sessionsWrote 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/instructions/gapmiss/claude-sessions/claude-md)<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.
<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>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 | $0.01458 | $0.01458 |
| Opus 5.5 | $0.00583 | $0.00583 |
| Sonnet 5.5 | $0.00292 | $0.00292 |
| Haiku 4.5 | $0.00146 | $0.00146 |
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.
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
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.
- 8d ago Changed 8ffcafa51933
- 20d ago Changed f1e90adf1604
- 27d ago Changed 0e452cd92964
- 28d ago Changed 8e6904fe5033
- 1mo ago Changed · +8 lines · +232 tokens per session 4aaa840b6d0c
- 1mo ago Changed · -18 lines · -272 tokens per session c389f8787094
- 2mo ago First seen · 105 lines · 1,498 tokens per session scan A c463400478d2
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.
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).
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.
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).
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.
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).
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.