Munder Difflin is a local multi-agent harness that turns terminal coding CLIs into a coordinated team of agents running on a user's machine. It is for people who want several supported coding agents to communicate, delegate work, retain memory, and operate through a shared office-style interface. The catalogue skills provide workflows for using and coordinating those agents.
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 skills add chaitanyagiri/munder-difflin --skill md-fetch-summarizegit clone --depth 1 https://github.com/chaitanyagiri/munder-difflinWrote 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/skills/chaitanyagiri/munder-difflin/md-fetch-summarize)<a href="https://agentmods.dev/skills/chaitanyagiri/munder-difflin/md-fetch-summarize"><img src="https://agentmods.dev/badge/skills/chaitanyagiri/munder-difflin/md-fetch-summarize/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/skills/chaitanyagiri/munder-difflin/md-fetch-summarize"><img src="https://agentmods.dev/badge/skills/chaitanyagiri/munder-difflin/md-fetch-summarize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00093 | $0.00279 |
| Opus 5.5 | $0.00037 | $0.00112 |
| Sonnet 5.5 | $0.00019 | $0.00056 |
| Haiku 4.5 | $0.00009 | $0.00028 |
Grade A, and why
md-fetch-summarize scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. Fetch the page with `WebFetch` (or `Bash` with `curl -sL <url> | head -200` as a fallback). What it actually says
Fetch & Summarize
Given a URL, fetch its content and return a concise markdown summary.
Steps:
- Fetch the page with
WebFetch(orBashwithcurl -sL <url> | head -200as a fallback). - Extract the main content — ignore nav, footer, ads, and boilerplate.
- Return a structured summary with:
- Title (the page's
<title>or heading) - One-paragraph overview of what the page is about
- Key points as a bullet list (max 5)
- Source — the URL fetched
- Title (the page's
Do not save or write the fetched content anywhere. Return the summary directly.
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.
- 1mo ago First seen · 29 lines · 93 tokens per session scan A 7acbda2b0e74
md-fetch-summarize is a skill published in the GitHub repository chaitanyagiri/munder-difflin (8,862 stars, last pushed 6d ago), licensed MIT. It adds 93 tokens to every session and 279 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
tacit.knowledge
Query the local tacit knowledge database (/.tacit/) for relevant context. TRIGGER when: user asks about topics that might have been previously captured — past conversations, meetings, decisions, ideas, learnings, or any domain knowledge. Also trigger when the user's question could benefit from previously stored…
tacit.memorize
Summarize the current session and save it to the tacit knowledge base (/.tacit/memory/). TRIGGER when: the user invokes /tacit.memorize, wants to save the current conversation to memory, or asks to record what was discussed. DO NOT TRIGGER for: querying existing knowledge (use /tacit.knowledge instead).
orient
At end-of-session, dispatches a read-only sub-agent to survey recent work and drafts a vaguely-specific priming prompt the next session can paste to orient itself and plan its next sprint. Produces orientation, not prescription — candidate directions are framed as questions, not decisions.
document-knowledge-base
Create and update a folder/file knowledge base using agentic discovery. Covers KB bootstrap, single entry creation, and entry updates. Use this when asked to document a system, subsystem, concept, or domain — or when existing KB entries need refreshing.
enso-reference
Show the enso system overview, skill directory, workflow, and live project status. Use when an agent or user needs a quick orientation to the current enso project's state, commands, and conventions.