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/jmstajim/dive-deeper-plugin/dive-deepernpx skills add jmstajim/dive-deeper-plugin --skill dive-deepergit clone --depth 1 https://github.com/jmstajim/dive-deeper-pluginWrote 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/jmstajim/dive-deeper-plugin/dive-deeper)<a href="https://agentmods.dev/skills/jmstajim/dive-deeper-plugin/dive-deeper"><img src="https://agentmods.dev/badge/skills/jmstajim/dive-deeper-plugin/dive-deeper.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 | $0.00039 | $0.00801 |
| Opus 5 | $0.00019 | $0.00400 |
| Sonnet 5 | $0.00008 | $0.00160 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
dive-deeper 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dive Deeper
The user feels the current analysis is incomplete — blind spots, unexplored paths, or risks that haven't been considered. Your job is to find them.
How to work
Actually search the codebase — don't reason from memory. Use Grep to find call sites, Glob to find related files, Read to examine implementations. Every claim ("this function is called from 3 places") must be backed by a tool call. If you haven't grepped for it, you don't know it.
If something is unclear — the intent behind the change, which behavior is expected, or how a component is supposed to work — ask the user before guessing. A wrong assumption baked into the analysis is worse than no analysis. Keep questions focused and specific.
What to do
1. Map the blast radius
Start from the function/type/file at the center of the change. Trace outward:
- Who calls this? Grep for all call sites — not just the obvious ones. Check tests, UI bindings, interface implementations, closures, dependency injection.
- Who does this call? Follow the dependency chain down. If you're changing a service, what does it depend on? Could those break?
- Who shares data with this? Look for shared state — globals, singletons, injected objects, config keys, file paths, notification/event names.
Build a concrete list of affected files with line numbers. Not "this might affect some views" — name them.
2. Trace the full flow
Pick the most important user-facing scenario that touches this code. Walk through it step by step:
- What triggers it?
- What state must exist before it works?
- What state does it leave behind after?
- What happens if it's interrupted halfway (process killed, network lost, concurrent call)?
If the change touches multiple flows, trace each one. Don't say "this could be a problem" — show the specific sequence of events that leads to failure.
3. Surface edge cases
Think about the inputs and states the original plan didn't consider:
- Empty/nil/zero: Empty collection? Nil value? Zero count?
- Boundaries: First item, last item, single item, maximum allowed.
- Concurrency & reentrancy: Can two callers hit this simultaneously? Can it be called while already running?
- Migration: Does this change the shape of persisted data? What happens to existing data?
- Partial failure: If this fails halfway, is the state consistent or half-updated?
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 · 75 lines · 39 tokens per session scan A cc86de658ade
dive-deeper is a skill published in the GitHub repository jmstajim/dive-deeper-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 801 once invoked, about $0.0002 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
watch
Watch live IDX turnover and order books for unusual activity — value surges, auto-reject approach, one-sided depth, walls appearing or withdrawn, quiet stocks waking up, UMA flags — plus delayed print-by-print attribution and end-of-day broker context. Use when the user runs /watch, or asks what is trading right now…
stockbit-status
Check whether the Stockbit session is still valid — main session expiry, whether trading credentials are stored, and the current trading mode. Use when the user asks "am I still logged in to Stockbit", "has my session expired", "is trading on", or when a stockbit MCP tool starts failing with an auth error.
stockbit-auth
Log in to Stockbit and capture the session for this server — opens the browser login flow and verifies the token was stored. Use when the user asks to log in or re-authenticate to Stockbit, or after a status check reports the session expired, HTTP 401, or logged out.
recursive-decomposition
Handle tasks that exceed the context window by decomposing them: size and filter the input, chunk it, run recursive sub-agents on independent parts, verify on small windows, and synthesise programmatically, following the Recursive Language Models (RLM) research by Zhang, Kraska and Khattab (2025). Use when a task…
bandar-check
Answer "who is accumulating this stock?" for an IDX ticker using Stockbit broker-flow data. Use when the user asks about bandar, big money, accumulation, distribution, foreign flow, asing, or who is on the other side of the tape.
trade-with-guardrails
Place an order through the user's own Stockbit account safely — check the mode, size the position from a risk budget, preview, read the summary back to the human, and only then write. Use when the user asks to buy, sell, amend or cancel an order, or to size a trade.