agentmods.dev

web-refresh

A command that fetches a previously cached web source again, ignoring its seven-day cache period. A cached source is saved online content used by other commands or documentation tools.

In plain words
What is it for?
Use it with a known source alias to re-crawl that source and replace its cached Markdown files.
Why use it?
It helps when the source has changed and the existing cached copy may be out of date.

Command

25 5d ago A scan 21 tokens original MIT
View the source file raintree-technology/docpull
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/raintree-technology/docpull/web-refresh
Clone the repo
git clone --depth 1 https://github.com/raintree-technology/docpull
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 365 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 $0.00021 $0.00365
Opus 5 $0.00010 $0.00182
Sonnet 5 $0.00004 $0.00073
Haiku 4.5 $0.00002 $0.00036

Measured yesterday against content hash 66b1ee4bd08a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-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.

plugin/commands/web-refresh.md · 32 lines

What it actually says

Refresh a cached web source

Force-refetch a source that's already cached. The default ensure_docs honors a 7-day cache; this command bypasses it.

User input: $ARGUMENTS

Workflow

  1. Parse $ARGUMENTS as a single source alias. If empty: reply Usage: /web-refresh <source>. Run /web-list to see what's cached. and stop.

  2. Call ensure_docs(source=<source>, force=true). The tool will re-crawl the source (using whatever URL the alias resolves to) and overwrite the cached .md files in place.

  3. If the alias is unknown: pass through the tool's error. Suggest /web-add <source> if it's a built-in or /web-add <name> <url> if not.

  4. After success, report a one-line summary using the tool's response (pages fetched / skipped / failed).

When to use this vs /web-add

  • /web-add <name> - first time fetching, or when the cache is fresh and you want to use it.
  • /web-refresh <name> - already cached but you want the latest. Don't run this every time you search; the conditional-GET cache makes it cheap, but it still hits the network for every page.

Don't

  • Don't loop this across all cached sources unprompted. If the user wants a global refresh, ask first.
  • Don't pass force=true to ensure_docs from any other command - that's what this command is for.
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 · 32 lines · 21 tokens per session scan A 66b1ee4bd08a

Subscribe to this mod's changes

web-refresh is a command published in the GitHub repository raintree-technology/docpull (25 stars, last pushed 5d ago), licensed MIT. It adds 21 tokens to every session and 365 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 2026-08-30.

Browser automationLanguagesWriting and docsai-training-datadeveloper-toolsdocumentationmarkdownpythonweb-scraping
Related

Other commands, from other repositories

check

Run all code quality checks and tests for the webdown project using the make all-checks target, which includes.

kelp/webdown · 0 tokens

release

Update CHANGELOG.md with changes since the last version increase. Check our README.md for any necessary changes. Check the scope of changes since the last release and increase our version number as apropraite.

kelp/webdown · 0 tokens

sync-config

Sync a scraping config's URLs against the live documentation site.

yusufkaraaslan/Skill_Seekers · 11 tokens

triage-prs

Daily DISCOVER→PLAN→EXECUTE→VERIFY→ITERATE triage of open PRs and issues.

1broseidon/ketch · 21 tokens

cli-anything-web:validate

Validate a cli-anything-web CLI against the tiered quality checklist (Tier 1 critical / Tier 2 comprehensive). Reports per-category and per-tier results.

ItamarZand88/CLI-Anything-WEB · 39 tokens

cli-anything-web:test

Run tests for a cli-anything-web CLI and update TEST.md with results.

ItamarZand88/CLI-Anything-WEB · 22 tokens