refresh

A command for rerunning analysis only on parts of a project that changed since the previous run. It also updates related documentation and the list of open issues.

In plain words
What is it for?
Refresh changed components, propagate interface changes, regenerate affected files, update documentation, and compare the current issue state with the previous baseline.
Why use it?
It avoids repeating analysis for unchanged components while still detecting deletions and changes that affect dependent parts. This makes incremental project maintenance more focused.

Command

Install

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.

agentmods
npx agentmods add commands/deepfusionlabs/deep-init/refresh
Clone the repo
git clone --depth 1 https://github.com/deepfusionlabs/deep-init
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 125 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.00125
Opus 5 $0.00012 $0.00063
Sonnet 5 $0.00005 $0.00025
Haiku 4.5 $0.00002 $0.00013

Measured yesterday against content hash 6739cfa2c456, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refresh 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.

commands/refresh.md · 8 lines

What it actually says

Run the deep-init skill in update mode (--update). Load skills/deep-init/SKILL.md and follow references/update.md: Step-0 symmetric set-diff change detection (authoritative; git advisory; deletions caught), DP-1 interface-hash propagation, always re-run the horizontal docs, then re-emit only the affected owned-region files and diff the issue baseline. Do not re-analyse unchanged components.

$ARGUMENTS

Changes

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.

  1. yesterday First seen · 8 lines · 23 tokens per session scan A 6739cfa2c456

Subscribe to this mod's changes

refresh is a command published in the GitHub repository deepfusionlabs/deep-init (6 stars, last pushed 13d ago), licensed MIT. It adds 23 tokens to every session and 125 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.