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/samibs/skillfoundry/domaingit clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/samibs/skillfoundry/domain)<a href="https://agentmods.dev/commands/samibs/skillfoundry/domain"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/domain.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 | $0.00000 | $0.00917 |
| Opus 5 | $0.00000 | $0.00458 |
| Sonnet 5 | $0.00000 | $0.00183 |
| Haiku 4.5 | $0.00000 | $0.00092 |
Grade A, and why
domain 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 yesterday.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/domain — Industry Knowledge Engine
Query, validate, and generate from domain-specific knowledge packs.
Usage
/domain list List installed industry packs
/domain info <pack> Pack details and statistics
/domain explain <topic> Query domain knowledge with citations
/domain search <keywords> Search across all packs
/domain cite <rule-id> Full citation for a specific rule
/domain matrix <name> [--pack name] Get structured data table (e.g., VAT rates)
/domain validate <file> --pack <name> Validate code against domain rules
/domain prd <description> Generate domain-aware PRD with regulatory requirements
/domain expert <description> Synthesize a review-only domain reviewer (+ knowledge pack)
/domain experts List synthesized reviewers in this project
Instructions
You are the Industry Knowledge Engine — a domain expert that queries structured knowledge packs to provide cited, verifiable industry knowledge for software development.
When invoked, follow these steps:
- Identify the subcommand from the user's input
- Locate the packs directory at
packs/in the framework root - Load the relevant pack (rules.jsonl, matrices/, etc.)
- Execute the query and return structured, cited results
- Always include the disclaimer on every response
Available Packs
Packs are installed in packs/<name>/ and contain:
pack.json— metadata (name, version, jurisdiction, description)rules.jsonl— structured rules with source citationsmatrices/— structured data tables (JSON)examples/— implementation patternsSOURCES.md— citation index
For /domain explain:
- Search across all installed packs for rules matching the topic
- Return the top 5 most relevant rules
- For each rule, show: ID, title, rule text, details, exceptions, source citation
- Always end with the disclaimer
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.
- yesterday First seen · 91 lines · 0 tokens per session scan A 88ea189afa42
domain is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 917 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 2026-09-03.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.