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 lastyeargit 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/lastyear)<a href="https://agentmods.dev/skills/chaitanyagiri/munder-difflin/lastyear"><img src="https://agentmods.dev/badge/skills/chaitanyagiri/munder-difflin/lastyear/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/lastyear"><img src="https://agentmods.dev/badge/skills/chaitanyagiri/munder-difflin/lastyear.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 | $0.00073 | $0.00298 |
| Opus 5.5 | $0.00029 | $0.00119 |
| Sonnet 5.5 | $0.00015 | $0.00060 |
| Haiku 4.5 | $0.00007 | $0.00030 |
Grade A, and why
lastYear scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
77% identical to last30Days — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
/lastYear
Get the concrete date range for the previous full calendar year by running the bundled resolver:
node "$AGENT_DIR/.claude/skills/temporal/when.mjs" lastYear
It prints a human-readable line plus a JSON record:
start/end— inclusive civil dates (YYYY-MM-DD) in your local timezonestartUtc/endExclusiveUtc— the same window as a half-open[start, end)range of exact UTC instants, for timestamp-based queriesdays,timezone,asOf— the span, your timezone, and when this resolved
Use the returned dates as the time bounds for the task at hand. Do not derive
dates by hand — this resolver is the source of truth. For the full window list
or an arbitrary range (e.g. last45days, last6months), see the /temporal skill.
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 · 30 lines · 73 tokens per session scan A cc96020c9c33
lastYear is a skill published in the GitHub repository chaitanyagiri/munder-difflin (8,862 stars, last pushed 5d ago), licensed MIT. It adds 73 tokens to every session and 298 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 77% identical to last30Days, differing in 14 lines, and is treated as a copy.
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…
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
wisdom-forget
Remove a must-keep CocoWisdom entry with rationale. Usage: $wisdom forget --id --rationale " ".
screenpipe-resume-work
Recover the last verified state of an interrupted task and identify the next useful action.
session-search
Use Moraine MCP tools to recover prior agent-session context when the user refers to earlier work, decisions, failures, branches, files, or other agents.
handoff
Save state at the end of a session, or resume from the last one. Triggers "wrapping up", "running out of context", "done for today", "continue where we left off", "resume".