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/ripemangobox/bite/domain-forknpx skills add RipeMangoBox/BITE --skill domain-forkgit clone --depth 1 https://github.com/RipeMangoBox/BITEWrote 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/ripemangobox/bite/domain-fork)<a href="https://agentmods.dev/skills/ripemangobox/bite/domain-fork"><img src="https://agentmods.dev/badge/skills/ripemangobox/bite/domain-fork.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 | $0.00055 | $0.01923 |
| Opus 5 | $0.00028 | $0.00962 |
| Sonnet 5 | $0.00011 | $0.00385 |
| Haiku 4.5 | $0.00006 | $0.00192 |
Grade A, and why
domain-fork 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 4d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domain Fork
Purpose
Migrate the core BITE architecture (collect/import local sources → download when needed → analyze → build index → query → ideate → focus → review) into a user-specified professional domain, and generate a complete domain-adapted skill set plus folder structure in one pass. This is a design-only legacy workflow. It is not part of the active paper analysis pipeline.
Trigger
Explicit invocation only. It should not be auto-triggered by description matching.
User must clearly request something like:
- "Fork a frontend development version of BITE"
- "Migrate BITE to the accounting domain"
- "Use domain-fork to create a journalism knowledge-base workflow"
Interactive Flow
After invocation, enter an interactive confirmation flow with no skipped steps:
Step 1: Domain confirmation
Confirm with the user:
- Target domain: e.g., "frontend development", "accounting/audit", "news production"
- Repository name: suggest
<Domain>Flow(e.g.,FrontendFlow,AccountingFlow,JournalismFlow), user can override - Save location: if not specified, default to
BITE/<RepoName>/and prompt:
"Default output path is BITE//. Do you want to change it?"
Step 2: Concept mapping table
Generate a BITE → target-domain concept mapping table for user confirmation/edit:
| BITE concept | Mapped target-domain concept | Notes |
|---|---|---|
| paper | (domain equivalent) | e.g., technical article, regulation document, news story |
| (domain equivalent) | e.g., webpage article, regulation PDF, manuscript document | |
| venue | (domain equivalent) | e.g., technical blog/framework version, regulator source, media source |
| obsidian-vault/analysis | (domain equivalent) | e.g., technical notes, regulation interpretation, editorial analysis |
| obsidian-vault/index | (domain equivalent) | e.g., technical index, regulation index, topic index |
| obsidian-vault/paperPDFs | (domain equivalent) | e.g., original articles, source regulations, source manuscripts |
| obsidian-vault/ideas | (domain equivalent) | e.g., project proposals, audit strategies, topic plans |
| core_operator | (domain equivalent) | e.g., core technical strategy, core regulation clause, core news angle |
| primary_logic | (domain equivalent) | e.g., implementation flow, compliance-check flow, editorial flow |
| paper_list.csv | keep | main tracking log, with domain-adjusted columns |
| state: Wait→Downloaded→analysised→checked | keep or adapt | state machine may need domain adaptation |
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.
- 4d ago First seen · 159 lines · 55 tokens per session scan A 099d708a92fc
domain-fork is a skill published in the GitHub repository RipeMangoBox/BITE (60 stars, last pushed 21d ago), licensed MIT. It adds 55 tokens to every session and 1,923 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
compile-wiki
Merge source summaries into durable concept pages with backlinks, index entries, and explicit open questions.
ingest-sources
Review newly ingested raw sources and draft or update source summary notes in notes/Sources/.
qa-agent
Answer questions from the vault, then file durable insights back into the knowledge base.
research-workflow
Manage resumable research runs under research/ and coordinate the collect, review, report, import, and archive steps.
lint-heal
Scan the vault for contradictions, unsupported claims, structural weaknesses, and missing pages, then repair what is safe.
render-output
Convert vault content into downstream outputs like memos, reports, slide outlines, diagrams, and plot specifications.