Borrowing it
Nothing to install: this file belongs to eschatus/roll20-dm-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/eschatus/roll20-dm-mcp/master/.claude/commands/round.mdgit clone --depth 1 https://github.com/eschatus/roll20-dm-mcpWrote 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/commands/eschatus/roll20-dm-mcp/round)<a href="https://agentmods.dev/commands/eschatus/roll20-dm-mcp/round"><img src="https://agentmods.dev/badge/commands/eschatus/roll20-dm-mcp/round.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 | $0.00000 | $0.01428 |
| Opus 5 | $0.00000 | $0.00714 |
| Sonnet 5 | $0.00000 | $0.00286 |
| Haiku 4.5 | $0.00000 | $0.00143 |
Grade A, and why
round 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Round Narration Parser
The DM is about to narrate what happened this round — spoken (voice-to-text) or typed. Parse it into a structured list of map actions and execute on confirmation.
Operating rules: follow @skills/dm-rules.md (write-safety, never auto-advance, conditions/
deaths/wounds, aura-vs-zone, narration cadence, voice-to-text resolution, real tool names). This
file covers the round-parsing choreography and the state snapshot.
Step 0: Write the round state snapshot
At the end of every round (after narration posts), overwrite
C:\Users\escha\.claude\projects\e--personalProjects-roll20-dm-mcp\memory\session-combat-state.md
with the current combat state. Keeps context recoverable if compression happens mid-fight.
Format:
---
name: session-combat-state
description: Current combat state — overwritten every round
metadata:
type: project
---
Round N — [Encounter name]
ACTIVE ENEMIES:
- Name: HP/maxHP (conditions)
PCs:
- Name: HP/maxHP (conditions, death saves if applicable) | Slots: L1:used/max L2:used/max … | Concentration: spell or none
DEAD THIS FIGHT: comma-separated names
Round N events: [2-3 sentence summary]
The snapshot is the only PC bookkeeping there is. This server has no D&D Beyond bridge —
there is no ddb_get_character to spot-check against, and nothing here reports spell slots or
prepared spells. So the snapshot is the sole authority for slots, and for PC HP it is the
running record alongside the relay's tracked-HP state. Update it whenever a PC casts or takes
damage. (If a separate DDB lookup server is connected, its reads can corroborate HP and
conditions — never slots — but that is not a tool of this server and it never writes.)
Step 1: Orient
If you don't already have current state in context, call list_tokens and get_turn_order
(who's on the map, what layer, current HP). Call get_recent_chat limit=30 for this round's
Beyond20 rolls — attack/damage totals you'll need to fill in numbers the DM doesn't state.
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 · 118 lines · 0 tokens per session scan A 4a84bc241161
round is a command published in the GitHub repository eschatus/roll20-dm-mcp (7 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,428 tokens. 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 2026-08-31.
Other commands, from other repositories
unity-test
Writes missing tests and runs them via MCP. Identifies untested code, creates EditMode/PlayMode tests, executes via runtests, reports results.
unity-optimize
Profile and optimize performance — uses MCP profiler for frame timing, memory, rendering stats. Identifies bottlenecks and applies fixes.
pop
Pop an item off the stash and continue working on it in the current session.
push
Push an idea onto the stash to handle later.
research
Delegate a broad codebase question to the troth-researcher subagent so the parent's context stays lean.
unity-feature
Plans and implements a Unity feature — identifies subsystems, loads skills, writes code, sets up scene elements via MCP.