Plugin Claude Code
DeepFusion Labs — DeepInit plugin marketplace.
6 12d ago A
tokens not measured
original MIT
deep-init
02Plugin Claude Code
Generates a grounded, verified, two-tier agent context layer (lean CLAUDE.md + deep .ai/docs) for any codebase, plus report-only issue detection. 100% local, read-only.
6 12d ago A
tokens not measured
original MIT
check
03Command
Is the context layer still true? 0-token staleness + broken-citation audit (no LLM, CI-friendly). Add --status for the fast hash-only subset.
6 12d ago A 36 tokens
original MIT
customize
04Command
Tune a DeepInit run with buttons — depth, issue detection, outputs, scope, cost, and the freshness/notification settings (disable the nudge, change its cadence/time-window) — no flags to type. Opens a native multiple-choice picker, then runs.
6 12d ago A 53 tokens
original MIT
doctor
05Command
DeepInit preflight — tools, scope, resolved config (and whether it's valid), enabled issue families, estimated cost. 0 tokens, no LLM. Offers to install the freshness hooks.
6 12d ago A 39 tokens
original MIT
fast
06Command
DeepInit quick pass — a full run with the review cycles skipped (faster, cheaper). Same as deep-init fast.
6 12d ago A 26 tokens
original MIT
help
07Command
Show all DeepInit commands + key options, grouped and ordered by how often you'll use them. Instant, no analysis.
6 12d ago A 24 tokens
original MIT
Command
Upgrade DeepInit to the latest version — pulls the newest from the marketplace (on one confirm), then guides the host-correct reload. Ends the "is my plugin stale?" dance.
6 12d ago A 37 tokens
original MIT
refresh
09Command
Refresh only what changed since the last run — incremental re-analysis of the touched components + issue lifecycle, on demand.
6 12d ago A 23 tokens
original MIT
translate
10Command
Emit the DeepInit report in another language (report. .html) — opens a language picker (buttons), or pass a code. English stays the canonical analysis output.
6 12d ago A 35 tokens
original MIT
version
11Command
Which DeepInit version is actually running right now? Prints the LOADED version, checks it against the on-disk version, and tells you if you need to reload. No analysis.
6 12d ago A 37 tokens
original MIT
SessionStart
12Hook
Runs when a session starts, executing session-start.sh. From deepfusionlabs/deep-init.
6 12d ago A
tokens not measured
copy · 61% MIT
Hook
Runs when you submit a prompt, before the agent sees it, executing session-start.sh. From deepfusionlabs/deep-init.
6 12d ago A
tokens not measured
copy · 61% MIT
deep-init
14Skill Claude CodeCodex
Generate an agent-agnostic, two-tier context layer for a codebase — a lean, always-loaded CLAUDE.md plus a deep, on-demand .ai/docs/ layer (business rules, live DB schema + ORM drift, cross-component workflows, and the WHY: ADRs + a knowledge log), every claim grounded to file:line and verified to exist. Built for…
6 12d ago A 128 tokens
original MIT
cursorrules
15Cursor rule Cursor
DeepInit projection provenance (R3) stage: EMIT → PROJECT (cursor) runid: run-2026-06-13-kemal-e2e source: AGENTS.md (lean tier) — deterministic projection, no new findings note: content inside the DEEPINIT markers is owned + regenerated; edit OUTSIDE them. -->.
6 12d ago A 1,687 tokens
original MIT
Instructions file GitHub Copilot
Instructions for deepfusionlabs/deep-init, covering repository instructions (copilot projection), kemal — agent context, architecture, components (7) and critical to know (non-obvious, load-bearing).
6 12d ago A 1,688 tokens
original MIT