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 commands/deepfusionlabs/deep-init/helpgit clone --depth 1 https://github.com/deepfusionlabs/deep-initWhat 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 | $0.00024 | $0.00474 |
| Opus 5 | $0.00012 | $0.00237 |
| Sonnet 5 | $0.00005 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
help 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
Print the DeepInit command overview exactly as below — a static reference card, NOT an analysis (no file reads, no detection, no tokens spent on the repo). Render it verbatim, then stop:
DeepInit — what you can run (start with a bare /deep-init; it already runs at max quality)
Everyday
/deep-init— full run at max quality: 2 adversarial review cycles, plus an automatic 3rd if the analysis isn't yet clean + deepest analysis + issues + report + SARIF./deep-init:fast— quick pass: review cycles skipped (0), faster and cheaper./deep-init:refresh— refresh only what changed since the last run./deep-init:translate— emit the report in another language (Spanish · Chinese · Portuguese · Russian · Japanese · German · French · Hebrew, or any other) — opens a language picker; English stays canonical.
Check & tune
/deep-init:check— "is it still true?" 0-token staleness + broken-citation audit (add--statusfor the fast hash-only subset)./deep-init:customize— tune the run with buttons (depth · issues · outputs · scope · cost · hooks) — no flags to type./deep-init:doctor— preflight: tools, scope, resolved config, enabled families (0 tokens); offers to install the freshness hooks.
Reference
/deep-init:version— which DeepInit version is actually running (and whether you need to/reload-plugins)./deep-init:plugin-update— update DeepInit to the latest version (one confirm) and guide the reload./deep-init:help— this overview.
Power users: every option is also a --flag (see the skill's reference), a key in the schema-validated .ai/deepinit.config, or just plain English — "do a quick pass, skip the database." Nothing needs to be memorized.
After printing, take no further action unless the user asks.
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 · 32 lines · 24 tokens per session scan A 6b3f00794767
help is a command published in the GitHub repository deepfusionlabs/deep-init (6 stars, last pushed 13d ago), licensed MIT. It adds 24 tokens to every session and 474 once invoked, about $0.0001 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 commands, from other repositories
fleet-conformance
Scan every repo on the machine for guardrails, testing, and observability conformance; audit the deltas semantically; produce a fleet report; and propose canary-first remediation.
claude-md-migrate
Rewrite a bloated or stale CLAUDE.md into a lean, verified "map, not wishes" file — nothing invented, hard rules preserved verbatim.
claude-md-new
Scaffold a CLAUDE.md for this repo from battle-tested templates, filled in with the project's real commands.
implement-review
One agent implements a task, then reviews its own work behind a hard verification gate before finalizing.
project-init
Stand up the context layers for a project — a thin pointer-style AGENTS.md plus seed compass maps — without touching the memory layer.
claude-md-audit
Grade this repo's CLAUDE.md / AGENTS.md (0–100) and return a worst-first fix list.