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 agents/aitit-inc/leadace/web-readergit clone --depth 1 https://github.com/aitit-inc/leadaceWhat 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 | $0.00049 | $0.00375 |
| Opus 5 | $0.00024 | $0.00187 |
| Sonnet 5 | $0.00010 | $0.00075 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
web-reader 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 12 lines · 49 tokens per session scan A ff15883994c3
web-reader is an agent published in the GitHub repository aitit-inc/leadace (1 stars, last pushed yesterday), with no licence file. It adds 49 tokens to every session and 375 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 agents, from other repositories
list-builder
Build company or contact seed lists for GTM workflows. Use for discovery, TAM building, portfolio prospecting, known-company contact finding, and provider-driven list construction before enrichment.
execution-plan-creator
Create a concrete Deepline execution plan before running GTM work. Use when the task needs routing, sequencing, provider selection, approval gating, or a plan that maps cleanly onto the skill docs.
pipeline-architect
Use to design and build a new Genudo pipeline end to end — from a business goal to a live, product-aware AI sales/support agent with stages, variables, and automations. Delegates the multi-step discovery, authoring, and provisioning. Use proactively when the user wants to create or set up a new pipeline, funnel, or…
pipeline-migrator
Use to migrate a Genudo pipeline built with an old instructions approach — legacy persona, global instructions, stage instructions, or stage structure — to the current authoring approach. Takes the old artifacts (pasted, from files, or pulled live from the account) and rebuilds or updates the pipeline against today's…
automation-engineer
Use to build integrations and automations on a Genudo pipeline — webhook actions to Zapier, Make, n8n, CRMs, or Google Sheets, with the variables that feed them. Handles variable types, payload mapping, triggers, and action-to-action chaining. Use proactively when the user wants the agent to register leads, call an…
kb-librarian
Use to curate a Genudo pipeline's knowledge base — the knowledge tables the agent answers from and their rows — when the agent gives wrong or outdated facts. Use when the user reports wrong factual answers, wants to create or fill a knowledge table, or wants to verify what the agent retrieves.