A command that reports DomainTome's MCP usage from the current project's database, including calls, transferred data, estimated tokens, and breakdowns by tool and operation.

Use it after a DomainTome sync or for a selected time period with an ISO timestamp to review calls, errors, data volume, and tool or operation counts.

It makes usage patterns visible so you can see how often the MCP tools are called and which ones account for the traffic.

stats — Command by yacb2

Install

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.

agentmods

npx agentmods add commands/yacb2/domaintome/stats

Clone the repo

git clone --depth 1 https://github.com/yacb2/domaintome

Or install dt, the plugin that ships this one along with the rest of its 1 skill, 9 commands, 1 agent, 2 hooks, 1 MCP server.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 384 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00026	$0.00384
Opus 5	$0.00013	$0.00192
Sonnet 5	$0.00005	$0.00077
Haiku 4.5	$0.00003	$0.00038

Measured 2d ago against content hash a8a7fd467aae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stats 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 2d 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.

plugins/domaintome/commands/stats.md · 50 lines

What it actually says

Report DomainTome's own usage analytics: how many MCP calls have been made against this graph, the byte volume exchanged (with a rough token estimate), and a per-tool / per-op breakdown.

Steps

Run dt stats against the current project's DB. If $ARGUMENTS contains an ISO timestamp, pass it as --since:
```
dt stats [--since $ARGUMENTS]
```

Summarize the output in a tight block:

## DomainTome usage (<period>)

- Calls: N   (errors: N)
- Total exchanged: X KB  (~Y tokens)
- Input: X KB (~Y tokens)
- Output: X KB (~Y tokens)

### By tool
- dt_add_node: N calls · X KB (~Y tokens)
- dt_audit: N calls · X KB (~Y tokens)
- ...

### By op
- audit / read / create / update / delete counts.

Honest proxy note: the CLI does not measure true tokens; the column is bytes × 0.3, useful for relative comparisons between tools or time periods, not for billing-grade numbers. Mention this only if the user asks for precision.

When to use

After a /dt:sync (INIT or EXTEND mode) to see what the seed/extend pass cost.
Periodically to spot unusually hot tools.
With --since <yesterday> to scope to a session.

Changes

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.

2d ago First seen · 50 lines · 26 tokens per session scan A a8a7fd467aae

Subscribe to this mod's changes

stats is a command published in the GitHub repository yacb2/domaintome (0 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 384 once invoked, about $0.0001 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 2026-08-31.

Analytics and metrics claude-code claude-code-plugin developer-tools knowledge-graph llm-agents llm-tools

resume

Auto-detect and resume any interrupted Plan Cascade task. Detects mega-plan, hybrid-worktree, or hybrid-auto context and routes to the appropriate resume command.

Taoidle/plan-cascade · 32 tokens

spec-plan

Run a resumable spec interview to produce spec.json/spec.md (planning-time), then optionally compile to prd.json. Usage: /plan-cascade:spec-plan " " [--output-dir ] [--flow ] [--first-principles] [--max-questions N] [--feature-slug ] [--compile] [--tdd ] [--confirm] [--no-confirm].

Taoidle/plan-cascade · 99 tokens

gsd:eval-review

Audit an executed AI phase's evaluation coverage and produce an EVAL-REVIEW.md remediation plan.

mrboups/xbrain · 26 tokens

discovery-ping

Discovery-plugin self-test. Exercises the plugin-shipped slash command path so we can capture commandsource/expansiontype values via the hook dumps.

dominiek/promptcellar-for-claude-code · 29 tokens

approve

Approve the current PRD and begin parallel story execution. Analyzes dependencies, creates execution batches, launches background Task agents for each story, and monitors progress. Usage: /plan-cascade:approve [--flow ] [--tdd ] [--confirm] [--no-confirm] [--agent ] [--impl-agent ] [--retry-agent ] [--no-verify]…

Taoidle/plan-cascade · 119 tokens

speckit.tasks

Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.

SteveGrosbois/tidal-cli · 18 tokens