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/dhevenddra/forensic-deepdive/codebase-onboardingnpx skills add Dhevenddra/forensic-deepdive --skill codebase-onboardinggit clone --depth 1 https://github.com/Dhevenddra/forensic-deepdiveWhat 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 | $0.00139 | $0.00655 |
| Opus 5 | $0.00069 | $0.00328 |
| Sonnet 5 | $0.00028 | $0.00131 |
| Haiku 4.5 | $0.00014 | $0.00065 |
Grade A, and why
codebase-onboarding 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.
What it actually says
Codebase onboarding
The first-day brief. One pass through all five artifacts, ordered for a new engineer.
When to use
- User explicitly signals they are new to this codebase / team.
- Question shape: 'onboard me', 'what should I know', 'give me the first-day brief', 'I'm new here'.
When NOT to use
- User has a specific task (bug, feature, refactor) → use the targeted skill.
- User is mid-task and asks a focused question → use
codebase-exploringorcodebase-debugging.
How to answer — read in this order
docs/codebase/AGENT_BRIEF.md(≤ 5 KB) — the never/always rules, the load-bearing symbol, the coupling rules. This is the floor; everything else is depth.docs/codebase/MENTAL_MODEL.md— entry points, layers, domains. The 'what is this product' answer.docs/codebase/MAP.md— most central files, key definitions. Where the weight is.docs/codebase/HOTPATHS.md— hot spots, cross-file dependencies, churn × centrality. What's actively changing.docs/codebase/ARCHAEOLOGY.md— top contributors with share %, bus factor, recent commits. Who to ask about what.
Surface ownership
After the read-through, name the top 3 contributors by share % from ARCHAEOLOGY.md and what they own (most-touched files). Bus-factor warnings go up front. A new engineer needs to know whose code they're about to step on.
Citation rule
Cite every artifact line: docs/codebase/AGENT_BRIEF.md:12, docs/codebase/ARCHAEOLOGY.md:34. The brief should be navigable, not a paraphrase.
What to report back
- One-paragraph 'what is this product' summary from MENTAL_MODEL.
- 5 named load-bearing files with one-line descriptions from MAP.
- Top 3 contributors with share % and the files they own from ARCHAEOLOGY.
- Every 'Always' rule from docs/codebase/AGENT_BRIEF.md, verbatim.
- Suggested next-step skill: 'for a specific bug, switch to
codebase-debugging; for a change,codebase-impact-analysis.'
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 First seen · 38 lines · 139 tokens per session scan A ded54fbf4d79
codebase-onboarding is a skill published in the GitHub repository Dhevenddra/forensic-deepdive (2 stars, last pushed 17d ago), licensed Apache-2.0. It adds 139 tokens to every session and 655 once invoked, about $0.0007 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 skills, from other repositories
manim-composer
Trigger when: (1) User wants to create an educational/explainer video, (2) User has a vague concept they want visualized, (3) User mentions "3b1b style" or "explain like 3Blue1Brown", (4) User wants to plan a Manim video or animation sequence, (5) User asks to "compose" or "plan" a math/science visualization.…
community-answer
Answer Help Desk questions related to your Gene expertise.
scienceworld-circuit-builder
This skill constructs a simple electrical circuit by connecting components like batteries, wires, and light bulbs. Use when the agent needs to test electrical conductivity or create a functional circuit for an experiment. The input is a set of available components, and the output is a fully connected circuit ready for…
scienceworld-heating-apparatus-setup
This skill positions a container with a substance onto a heating device (stove, oven) and activates the device. It should be triggered when a task requires melting, boiling, or heating a substance. The skill moves the prepared container to the heating element and turns it on.
slack-docs
Use when answering a conceptual or how-to question about Slack platform features, or when asked to look up, fetch, or summarize a docs.slack.dev page, including a pasted docs.slack.dev link. Covers finding and reading official Slack docs as clean markdown.
onboarding
Onboarding tour for first-time omo users.