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/checkgit 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 | $0.00036 | $0.00363 |
| Opus 5 | $0.00018 | $0.00181 |
| Sonnet 5 | $0.00007 | $0.00073 |
| Haiku 4.5 | $0.00004 | $0.00036 |
Grade A, and why
check 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 yesterday.
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
Run the deep-init skill's staleness check — no LLM, no network, 0 tokens (any model call here is a bug). This is the unified front door over the two free checks (the --status and --lint flags stay available for hooks / CI):
- Status (deterministic keystone — always runs first). Execute the status keystone and report its output verbatim:
python .ai/deepinit_status.py # if setup-hooks has installed it into this repo
# else, from the plugin: python skills/deep-init/assets/deepinit_status.py
It compares .ai/docs/current/.file_hashes.json against the working tree (modified / removed via the Step-0 symmetric set-diff / pending). Exit 0 = fresh, 1 = stale.
- Lint (citation + coverage audit — when generated docs exist AND
--statuswas NOT passed). Followreferences/update.md's--lintflow: per-component fresh/stale/critical staleness, broken-reference (deadfile:line) detection, ID consistency, and coverage — all by hash/citation comparison, still 0 tokens. Non-zero exit on a critical/dead citation (the CI gate).
If it reports STALE, offer to run /deep-init:refresh. Report the result; do not modify anything. See references/triggers.md and references/update.md.
$ARGUMENTS
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.
- yesterday First seen · 22 lines · 36 tokens per session scan A b2d5c6bd3ee4
check is a command published in the GitHub repository deepfusionlabs/deep-init (6 stars, last pushed 12d ago), licensed MIT. It adds 36 tokens to every session and 363 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 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.