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/zaxbyhub/opencode-swarm/deep-divenpx skills add ZaxbyHub/opencode-swarm --skill deep-divegit clone --depth 1 https://github.com/ZaxbyHub/opencode-swarmWrote 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/zaxbyhub/opencode-swarm/deep-dive)<a href="https://agentmods.dev/skills/zaxbyhub/opencode-swarm/deep-dive"><img src="https://agentmods.dev/badge/skills/zaxbyhub/opencode-swarm/deep-dive.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 | $0.00066 | $0.02681 |
| Opus 5 | $0.00033 | $0.01340 |
| Sonnet 5 | $0.00013 | $0.00536 |
| Haiku 4.5 | $0.00007 | $0.00268 |
Grade A, and why
deep-dive 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Dive Audit Protocol
Read-only deep audit of a specified codebase scope using parallel explorer waves, always 2 parallel reviewers, and sequential critic challenge. This mode does NOT mutate source code, does NOT delegate to coder, and does NOT call declare_scope.
Graph-first evidence contract
Use repo_map graph_health and boundary discovery before a targeted source-bearing context_pack; existing ask, key_files, and localization remain discovery inputs. Graph evidence is advisory only. If freshness is stale or inconclusive, confidence is low, source is missing, the language is unsupported/dynamic, the graph is absent, or an action fails, inspect the direct source and searches before reporting a finding.
MODE: DEEP_DIVE
Step 0 — Parse Header
Parse the MODE: DEEP_DIVE header to extract:
scope: the codebase area to audit (e.g., "auth", "payment flow", "src/hooks/")profile: one of standard | security | ux | architecture | full (default: standard)max_explorers: integer 1..8 — upper bound on explorer waves (default: 6, or 8 for full profile). This is a CAP, not a fixed count: scale the actual wave size to the resolved scope surface — a trivial scope needs 1–2 explorers, a typical scope 3–5, a large multi-module scope up to the cap — never fix the count in advance.output: markdown | json (default: markdown)update_main: boolean (default: true) — whether to fetch/ff-only main before startingallow_dirty: boolean (default: false) — whether to proceed with uncommitted changes
If the header is malformed or missing required fields, report the error and stop.
Step 1 — Repo Readiness
- Check git working tree status. If dirty and
allow_dirtyis false, warn the user and ask whether to proceed. Do NOT proceed automatically. - If
update_mainis true and tree is clean: check current branch. If not onmain, report current branch to user and ASK FOR CONFIRMATION before switching. Only after explicit user approval:git fetch origin main && git checkout main && git merge --ff-only origin/main. If ff-only fails, warn the user and ask before proceeding. - Record the current HEAD commit hash for the report.
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 · +4 lines ae0bf9b91c4b
- 6d ago First seen · 161 lines · 66 tokens per session scan A 71c852323071
deep-dive is a skill published in the GitHub repository ZaxbyHub/opencode-swarm (464 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 2,681 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
ux-create-manifest
Create the initial Product UX Bible for an existing web or full-screen web app by deeply auditing the repository, using sub-agents when available, and generating docs/ux manifests, schemas, budgets, surface maps, action taxonomy, and design-token policies from observed code.
ux-principal
Principal UX architect skill for deciding WHERE a UI feature belongs, before it is implemented. Reads and maintains docs/ux manifests, classifies the feature, decides placement, navigation, surface, action hierarchy and complexity budgets, and produces a precise implementation brief without coding unless explicitly…
full_unpackd_rep
Use when the task is to unpack a local reference repository into a Chinese structural topic page, update site navigation, stamp dates, and leave behind a reusable deconstruction note for the repo.
gen-zhihu-article
Generate Zhihu article in the style of 22-庖丁解牛专题页-知乎图文终版.md.
loloop
Use when a task should advance through repeated plan-driven loop cycles for an engineering project, paper, or long-running repo change. loloop wraps the official /loop idea with the repo's loop-in-loop method: read the current plan, inspect prior evolution notes, execute the current iteration, write a new evolution…
zhihu-publish
Use when the task is to publish a Zhihu article from Markdown using the local browser-automation pipeline in this repo. Covers the text-only publishing chain, the multimodal chain that uploads Markdown images into the Zhihu editor, cookie-based login checks, and choosing between the stable text script and the richer…