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.
npx agentmods add instructions/oksr/wdist/claude-mdgit clone --depth 1 https://github.com/oksr/wdistWrote 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/oksr/wdist/claude-md)<a href="https://agentmods.dev/instructions/oksr/wdist/claude-md"><img src="https://agentmods.dev/badge/instructions/oksr/wdist/claude-md.svg" alt="Measured on agentmods" 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 | $0.01565 | $0.01565 |
| Opus 5 | $0.00783 | $0.00783 |
| Sonnet 5 | $0.00313 | $0.00313 |
| Haiku 4.5 | $0.00156 | $0.00156 |
Grade A, and why
wdist 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 4d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this repo is
A Claude Code plugin (wdist) that ships a single slash command, /wdist, which generates a shareable daily recap of the user's Claude Code sessions. The directory layout is dictated by Claude Code's plugin spec — .claude-plugin/plugin.json and .claude-plugin/marketplace.json are the entry points, commands/*.md are slash commands, scripts/ holds anything those commands shell out to.
Architecture: dumb extractor + smart prompt
The plugin is deliberately split into two pieces that should stay decoupled:
-
scripts/recap-day.py— a dependency-free Python 3 extractor. Walks~/.claude/projects/<encoded-cwd>/<session-id>.jsonl(Claude Code's per-session transcripts), filters records to those with timestamps inside the target local-day window, and emits a compact JSON document to stdout. No summarization happens here. Its job is purely to surface raw signal (titles, first/last messages, prompt list, counts, cwd) with sensitive payloads truncated to fixed byte limits. -
commands/wdist.md— the slash command. Parses$ARGUMENTS(an optionalYYYY-MM-DDdate and an optional--verboseflag), runs the extractor, reads the JSON from/tmp/recap-${DATE}.json, then instructs Claude to synthesize the recap. All editorial logic — tone, what counts as "shipped" vs. "in progress", redaction rules, short-vs-verbose format — lives in this prompt. If you're tempted to add summarization logic to the Python script, push it into the prompt instead; if you're tempted to add a heavy dependency, find another way.
Output is written to ~/claude-recaps/YYYY-MM-DD.md (overwrite on re-run is expected) and also rendered inline in the chat for copy-paste.
Working on the extractor
Run it directly to iterate without going through the slash command:
python3 scripts/recap-day.py # today
python3 scripts/recap-day.py 2026-04-15 # specific date
python3 scripts/recap-day.py 2026-04-15 | jq '.sessions[0]'
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.
- 4d ago First seen · 89 lines · 1,565 tokens per session scan A fcc91c268645
wdist CLAUDE.md is an instructions file published in the GitHub repository oksr/wdist (5 stars, last pushed 2mo ago), licensed MIT. It adds 1,565 tokens to every session, about $0.0078 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 2026-08-31.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.