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 last30daysgit 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/last30days)<a href="https://agentmods.dev/skills/chaitanyagiri/munder-difflin/last30days"><img src="https://agentmods.dev/badge/skills/chaitanyagiri/munder-difflin/last30days.svg" alt="Measured on agentmods" 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 | $0.00083 | $0.00313 |
| Opus 5 | $0.00042 | $0.00156 |
| Sonnet 5 | $0.00017 | $0.00063 |
| Haiku 4.5 | $0.00008 | $0.00031 |
Grade A, and why
last30Days scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
8 near-identical copies found in the catalogue:
- last7Days — 89% identical, 14 lines differ
- yesterday — 89% identical, 14 lines differ
- lastQuarter — 88% identical, 14 lines differ
- lastWeek — 88% identical, 14 lines differ
- today — 84% identical, 14 lines differ
- thisMonth — 78% identical, 14 lines differ
- lastMonth — 77% identical, 14 lines differ
- lastYear — 77% identical, 14 lines differ
What it actually says
/last30Days
Get the concrete date range for a rolling 30-day window ending today by running the bundled resolver:
node "$AGENT_DIR/.claude/skills/temporal/when.mjs" last30Days
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.
- 8d ago First seen · 30 lines · 83 tokens per session scan A baafbc6a0d24
last30Days is a skill published in the GitHub repository chaitanyagiri/munder-difflin (6,519 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 313 once invoked, about $0.0004 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…
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.
enso-session-persist
Persist only the session state that improves future re-entry, coordination, or reuse.
read-session-logs
Display recent enso session logs and show a summary of active stories. Use when reviewing past sessions, auditing project history, or getting oriented on session continuity. Read-only — no files are modified.
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…