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/raintree-technology/docpull/web-listgit clone --depth 1 https://github.com/raintree-technology/docpullWhat 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 | $0.00014 | $0.00250 |
| Opus 5 | $0.00007 | $0.00125 |
| Sonnet 5 | $0.00003 | $0.00050 |
| Haiku 4.5 | $0.00001 | $0.00025 |
Grade A, and why
web-list 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
List cached web sources
Show what's available to /web-search right now.
Workflow
-
Call
list_indexed(). It returns source aliases that have been fetched, with file count and how long ago they were fetched. -
If empty: reply with a one-liner pointing to
/web-addandlist_sourcesfor the built-in alias list. Don't fetch anything. -
If non-empty: render the list as the tool returned it (it's already formatted). Note any sources marked
stale(older than 7 days) and suggest/web-refresh <source>for those if there are any. -
If the user is likely going to follow up with a search, suggest
/web-search <pattern> [source]once at the bottom.
Don't
- Don't crawl, fetch, or call
ensure_docsfrom this command. It's a read-only listing. - Don't expand each source's file tree -
list_indexedsummarizes for a reason.
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 · 24 lines · 14 tokens per session scan A 62753a005f86
web-list is a command published in the GitHub repository raintree-technology/docpull (25 stars, last pushed 6d ago), licensed MIT. It adds 14 tokens to every session and 250 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.
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.
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.
sync-config
Sync a scraping config's URLs against the live documentation site.
triage-prs
Daily DISCOVER→PLAN→EXECUTE→VERIFY→ITERATE triage of open PRs and issues.
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.
cli-anything-web:test
Run tests for a cli-anything-web CLI and update TEST.md with results.