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 commands/usathyan/epistract/domain-listgit clone --depth 1 https://github.com/usathyan/epistractWrote 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/usathyan/epistract/domain-list)<a href="https://agentmods.dev/commands/usathyan/epistract/domain-list"><img src="https://agentmods.dev/badge/commands/usathyan/epistract/domain-list.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 | $0.00031 | $0.00685 |
| Opus 5 | $0.00015 | $0.00342 |
| Sonnet 5 | $0.00006 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
epistract-domain-list 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/epistract:domain-list
List all installed domains — both active and archived — in a formatted table. Shows entity
type count, relation type count, last-modified date, and pipeline status for each domain.
Active domains are available to the pipeline; archived domains are excluded from resolution
but kept on disk at domains/_archived/<name>/.
Usage Guard
If invoked with --help: Display the following and stop. Otherwise proceed to Steps.
Usage: /epistract:domain-list
Lists all installed domains with:
- Name
- Entity type count
- Relation type count
- Last-modified date (from domain.yaml mtime)
- File count
- Status (active / archived)
Archived domains are excluded from the pipeline but kept on disk.
To remove a domain: /epistract:domain-delete <name>
To create a new domain: /epistract:domain
Steps
Step 1: Fetch domain data
Run:
python3 scripts/manage_domains.py list
- If the command exits non-zero: display the error output and stop. Suggest running
/epistract:setupif the script is missing or the environment is misconfigured. - If the output is an empty JSON array (
[]): report "No domains installed. Run/epistract:domainto create one." and stop. - If successful (exit 0, non-empty array): proceed to Step 2.
Step 2: Format and display
Parse the JSON array returned by Step 1.
Separate rows into two groups:
- Active — rows where
status == "active" - Archived — rows where
status == "archived"
Display active domains as a markdown table:
| Name | Entity Types | Relation Types | Last Modified | Files |
|------|-------------|----------------|---------------|-------|
| contracts | 9 | 9 | 2026-04-23 | 11 |
| drug-discovery | 17 | 30 | 2026-04-20 | 8 |
If archived rows exist, display a second table beneath the first:
### Archived Domains
The following domains are archived and excluded from the pipeline.
Run `/epistract:domain-delete <name>` to permanently remove an archived domain.
| Name | Entity Types | Relation Types | Last Modified | Files |
|------|-------------|----------------|---------------|-------|
| old-domain | 2 | 1 | 2026-03-10 | 3 |
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 · 88 lines · 31 tokens per session scan A 32250fd2b79a
epistract-domain-list is a command published in the GitHub repository usathyan/epistract (8 stars, last pushed 21d ago), licensed MIT. It adds 31 tokens to every session and 685 once invoked, about $0.0002 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 commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
release
Perform a full release: generate release notes, bump version, commit, tag, and push.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.