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-hive-syncgit 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-hive-sync)<a href="https://agentmods.dev/skills/chaitanyagiri/munder-difflin/md-hive-sync"><img src="https://agentmods.dev/badge/skills/chaitanyagiri/munder-difflin/md-hive-sync.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 5.1 | $0.00109 | $0.00334 |
| Opus 5 | $0.00055 | $0.00167 |
| Sonnet 5 | $0.00022 | $0.00067 |
| Haiku 4.5 | $0.00011 | $0.00033 |
Grade A, and why
md-hive-sync 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 7d 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.
What it actually says
Hive Sync
Run the mandatory hive start-of-task steps:
-
Read memory —
Read $AGENT_DIR/memory.mdfor durable context from prior sessions. -
Check inbox — list and read all files in
$AGENT_DIR/inbox/that are NOT ininbox/.done/. For each message:- Act on the message.
- Move the handled file into
$AGENT_DIR/inbox/.done/withmv.
-
Report — summarize what you found in memory and any new inbox messages. Note any tasks assigned to you or information relevant to the current session.
-
End-of-task reminder — before closing this conversation, append durable facts, decisions, and outcomes to
$AGENT_DIR/memory.mdso future-you remembers.
Run echo $AGENT_DIR if the variable is not set to locate your agent directory under the hive root.
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.
- 7d ago First seen · 32 lines · 109 tokens per session scan A d1fcef3338b2
md-hive-sync is a skill published in the GitHub repository chaitanyagiri/munder-difflin (6,455 stars, last pushed today), licensed MIT. It adds 109 tokens to every session and 334 once invoked, about $0.0005 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 2026-08-30.
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…
pod-resume
Reconstruct context for a returning developer. Reads .cocoplus/ state and generates a narrative summary of project status, last achievements, pending tasks, recent decisions, available patterns, CocoCupper insights, and recommended next action.
td-task-management
Task management for AI agents across context windows. Use when agents need to track work, log progress, hand off state, and maintain context across sessions. Includes workflows for single-issue focus, multi-issue work sessions, and structured handoffs. Essential for AI-assisted development where context windows reset…
task-register
Register a new task that does not yet have a GitHub Issue in the Hyper-Waterfall workflow. Query open milestones and existing labels, choose candidates, confirm with the task requester before creating the Issue, then create the GitHub Issue number. After Issue creation, hand off branch, daily task board, and task plan…
task-final-report
Apply the final report and PR publication procedure for a Hyper-Waterfall task. Write the final report (report.md), mark the daily task board complete, create the final commit, push the remote publish/task{N} branch, and create an Open PR to {BASEBRANCH}. Invoke only immediately before PR publication after all stages…
todo
Create and update the Hyper-Waterfall daily task board (mydocs/orders/yyyymmdd.md). Apply milestone table format, status update rules, and backlog section rules. When task-start, task-stage-report, task-final-report, or pr-merge-cleanup updates the daily task board, it follows this SKILL's format.