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 agentmods add skills/yacb2/domaintome/dt-usagenpx skills add yacb2/domaintome --skill dt-usagegit clone --depth 1 https://github.com/yacb2/domaintomeWrote 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/yacb2/domaintome/dt-usage)<a href="https://agentmods.dev/skills/yacb2/domaintome/dt-usage"><img src="https://agentmods.dev/badge/skills/yacb2/domaintome/dt-usage.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 | $0.00184 | $0.03167 |
| Opus 5 | $0.00092 | $0.01584 |
| Sonnet 5 | $0.00037 | $0.00633 |
| Haiku 4.5 | $0.00018 | $0.00317 |
Grade A, and why
dt-usage 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 5d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DomainTome — read-first, write-on-decision
This project ships with the DomainTome MCP server (dt_* tools) that stores
business knowledge as a typed graph: modules, capabilities, flows, events,
rules, forms, entities and decisions. Treat DomainTome as the project's living
memory.
Scope: where does "the project" live?
DomainTome has no opinion about whether a project is a single repo or a
workspace holding several repos/packages. The graph lives in
.dt/graph.db relative to whatever directory Claude Code was launched
from — that's the "root of analysis". Workspaces with multiple repos
(split-repo setups, monorepos of independent packages, *_ws/
scaffolding) typically keep .dt/ at the workspace root so a single
graph captures cross-repo relations. Single-repo projects keep it at the
repo root. Both are valid; pick whichever matches the unit of knowledge
you want to capture. The MCP server logs the resolved DB path on startup
so you can always verify which one it is using.
Read before acting
Before answering "how does X work?" or writing non-trivial code that touches a known concept, consult the graph:
dt_overview()— call this first when landing on a project. One compact payload with node counts, top capabilities, recent decisions and recent changes. Cheaper than several exploratory calls.dt_query(text_or_id, depth=1)—text_or_idis required. Exact id / title substring / tag.dt_list(type=..., include_body=False)— cheap summary scan; follow up withdt_get_nodefor detail. Returns{"items": [...]}.dt_get_node(id, include_edges=true)— full detail of a hit.dt_traverse(from_id, relations, max_depth)— blast radius.
"How many ways of doing X?" — use dt_query(text_or_id=<capability_id>, depth=1) and filter the returned edges for relation == "implements" with to_id == <capability_id>; the from_id of each matching edge is a flow variant.
If the graph has the answer, cite the node id(s). If it's silent, say so — don't fabricate.
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.
- 5d ago First seen · 258 lines · 184 tokens per session scan A 894697e8bb0d
dt-usage is a skill published in the GitHub repository yacb2/domaintome (0 stars, last pushed 3mo ago), licensed MIT. It adds 184 tokens to every session and 3,167 once invoked, about $0.0009 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.
Other skills, from other repositories
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…
memory-and-handoff
Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.
forget
Delete a Wenlan memory by exact id from Codex. Destructive and confirmation gated. Invoked as /forget .
agent-common
Shared preamble loaded by all cc10x agents — memory protocol, contract format, output rules.
memesh
Use MeMesh to remember, recall, and manage AI knowledge across sessions, and to exchange task-focused messages with local agents. Triggers when the user asks to remember something, recall past decisions, forget outdated info, learn from mistakes, analyze work patterns, contact another agent, or handle a memeshmessage…
handoff
End a Codex work session. Stores durable captures, writes a narrative session log, and automatically applies typed item-level deltas to the current Space Brief. Invoked as /handoff.