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 skills add OneDro1d/dark-factory --skill codebase-understandinggit 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/codebase-understanding)<a href="https://agentmods.dev/skills/onedro1d/dark-factory/codebase-understanding"><img src="https://agentmods.dev/badge/skills/onedro1d/dark-factory/codebase-understanding/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/onedro1d/dark-factory/codebase-understanding"><img src="https://agentmods.dev/badge/skills/onedro1d/dark-factory/codebase-understanding.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00073 | $0.00435 |
| Opus 5.5 | $0.00029 | $0.00174 |
| Sonnet 5.5 | $0.00015 | $0.00087 |
| Haiku 4.5 | $0.00007 | $0.00044 |
Grade A, and why
codebase-understanding 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 1mo 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.
What it actually says
Codebase Understanding (read-first, low-token)
Goal: locate the relevant code in the fewest tokens. NEVER scan the whole repo to answer a question the context store already answers.
Order of reading (stop as soon as you have what you need)
.claude/context/SERVICE-MAP.md— which service/db/queue/API owns this area..claude/context/FINDINGS.md— is this already known/solved?.claude/context/DECISIONS.md— is the current behavior intentional?- The ONE relevant
<service>/CLAUDE.md— contracts, key files, gotchas. - The shared-models
CLAUDE.md— only when tracing a routing key / RPC across services. - Source — targeted, by
file:linefrom the above, via Grep/Read. Not whole-file dumps unless necessary.
Cheap search patterns
- Routing key / RPC:
grep -rn "<routing.key>" <service>/then open the dispatcher. - A symbol:
grep -rn "MethodName\|TypeName" <service>/ --exclude-dir={obj,bin}. - A flow: start at the SERVICE-MAP "In → Out" column, follow the routing key to the next consumer.
Output
A short "where it lives" answer: service, file:line, and the one-line role. Do not paste large code blocks — cite locations.
Don't
- Don't re-derive the architecture; it's in SERVICE-MAP/CLAUDE.md.
- Don't read every service. Read the one(s) the map points to.
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.
- 1mo ago First seen · 30 lines · 73 tokens per session scan A abca92f2cda4
codebase-understanding is a skill published in the GitHub repository OneDro1d/dark-factory (4 stars, last pushed 6d ago), licensed Apache-2.0. It adds 73 tokens to every session and 435 once invoked, about $0.0003 per session on Opus 5.5. 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
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…