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/onedro1d/dark-factory/scope-initnpx skills add OneDro1d/dark-factory --skill scope-initgit clone --depth 1 https://github.com/OneDro1d/dark-factoryWrote 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/onedro1d/dark-factory/scope-init)<a href="https://agentmods.dev/skills/onedro1d/dark-factory/scope-init"><img src="https://agentmods.dev/badge/skills/onedro1d/dark-factory/scope-init.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 | $0.00203 | $0.03500 |
| Opus 5 | $0.00102 | $0.01750 |
| Sonnet 5 | $0.00041 | $0.00700 |
| Haiku 4.5 | $0.00020 | $0.00350 |
Grade A, and why
scope-init 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.
How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scope-init — stand up (or refresh) an agent-notepad
A notepad is one standalone git repo per objective, named <group>-<objective>
(e.g. proj-arbbot). The group is the prefix — the substring before the first
hyphen (proj-basket-tokens → group proj). Code lives in separate repos referenced
by repos.manifest.json and driven via absolute paths, never by cd-ing. This skill
creates that notepad or refreshes an existing one. See the design in
../../DESIGN.md (§5 topology, §6 file contracts, §7 hooks, §8 cross-repo bridge).
Consent is load-bearing. Two actions in this procedure touch the outside world and MUST NOT run without an explicit yes from the operator, each time:
- Creating a GitHub repo (
gh repo create). - Bootstrapping a df-context-store into a code repo you don't own the substrate of. Everything else is local file writes and read-only repo validation.
Idempotent. On a re-run in an existing notepad: refresh SCOPE.md / manifest /
CLAUDE.md and re-validate repos, but never clobber NOTES.md or any journal file —
merge/append only. A second scope-init is a safe no-harm refresh.
A re-run is not a shorter run. Steps 6 and 6a are per-REPO offers, and the repo set moves: a repo added to the manifest last month was never offered anything, because it did not exist when the offers were made. So a re-run walks every repo in the manifest, not only the ones this run created. ⚠️ First init is the one moment the repo set is complete by accident. After that, "it was offered" is a fact about the repos that existed then, and a step that runs only at init quietly stops covering the estate it claims to — the gap widening in exactly the direction nobody looks, because the notepad reports success either way.
Procedure
1. Resolve the group prefix and notepad name
- If the operator names the notepad (
proj-arbbot), take it. Otherwise ask for the objective in a few words and the group prefix, then propose<group>-<slug>(kebab-case slug of the objective). - Derive the group = prefix before the first hyphen. This is the memory
wingand the org-routing key. Confirm it with the operator before proceeding. - Read
../../plugin/notepad-template/org-routing.example.json(or the operator's ownorg-routing.jsonif present) to map prefix → GitHub org. If the prefix isn't in the map, ask which org (or fall back todefault_org) — do not guess silently.
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 Changed · +9 lines 6abb6ba10737
- 5d ago First seen · 221 lines · 203 tokens per session scan A 3ee49ca9e72f
scope-init is a skill published in the GitHub repository OneDro1d/dark-factory (0 stars, last pushed today), licensed Apache-2.0. It adds 203 tokens to every session and 3,500 once invoked, about $0.0010 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 2026-09-01.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…