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/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-hive-sync"><img src="https://agentmods.dev/badge/skills/chaitanyagiri/munder-difflin/md-hive-sync.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 | $0.00109 | $0.00334 |
| Opus 5.5 | $0.00044 | $0.00134 |
| Sonnet 5.5 | $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 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.
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.
- 1mo 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 (8,862 stars, last pushed 4d ago), licensed MIT. It adds 109 tokens to every session and 334 once invoked, about $0.0004 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 2026-08-30.
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…
wisdom-consolidation-log
View CocoWisdom consolidation exceptions. Usage: $wisdom consolidation-log.
register-project
Register an existing project in memory. Use when starting work on a new repo or when a project needs its own context file. Triggers on: 'register project', 'add project to memory', 'track this project', 'create project file'.
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…