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 skills add NOMARJ/sigil --skill icp-buildergit clone --depth 1 https://github.com/NOMARJ/sigilWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nomarj/sigil/icp-builder)<a href="https://agentmods.dev/skills/nomarj/sigil/icp-builder"><img src="https://agentmods.dev/badge/skills/nomarj/sigil/icp-builder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nomarj/sigil/icp-builder"><img src="https://agentmods.dev/badge/skills/nomarj/sigil/icp-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.00825 |
| Opus 5.5 | $0.00021 | $0.00330 |
| Sonnet 5.5 | $0.00010 | $0.00165 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
icp-builder 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ICP Builder
Pre-requisites
Invoke business-context skill first. Requires a GTM spec for this product.
What you build
A specific, usable ICP — not a persona cartoon. Something you can filter a LinkedIn search with. Something you can hand to an outreach sequence.
ICP Document Structure
Firmographic (company)
Industry: [specific vertical — not "tech"]
Company size: [headcount or ARR range]
Geography: [country/region — be specific]
Stage: [startup/scaleup/enterprise — not all three]
Tech indicators: [tools they use that signal fit]
Anti-fit: [company types that look right but never buy]
Demographic (person)
Title: [exact job titles — 2-3, not 10]
Seniority: [IC / manager / director / VP / C-suite]
Department: [function they sit in]
Reports to: [who they answer to]
Owns budget: [yes/no — or "influences"]
Decision maker: [yes/no — or "champion"]
Psychographic (mindset)
Pain they feel daily: [specific, not generic]
Fear they won't say out loud: [what keeps them up]
What success looks like: [measurable for them]
What they read/watch: [where they get information]
Who they trust: [peers, analysts, communities]
Trigger events
Trigger 1: [event that makes them go looking — be specific]
Trigger 2: [another event]
Signal: [how we would know this trigger just happened]
Disqualifiers
- [reason this company/person will never buy even if they look like ICP]
- [another disqualifier]
Per-product ICP notes
Sigil
The buyer is not the CISO. The CISO approves budgets. The buyer is the security engineer or DevSecOps lead who:
- Just had an incident involving an AI agent or MCP server
- Is being asked by their CISO to "do something about AI security"
- Has never had a tool specifically for auditing AI agent code
Trigger: company adopts Claude Code / Cursor / agentic workflows in production. Signal: GitHub shows active Claude Code use, MCP server repos, agent frameworks.
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.
- 1mo ago First seen · 113 lines · 52 tokens per session scan A a4bfbbb6b56f
icp-builder is a skill published in the GitHub repository NOMARJ/sigil (6 stars, last pushed 11d ago), licensed Apache-2.0. It adds 52 tokens to every session and 825 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
sftp-cc
A natural-language SFTP tool for uploading local project files to a remote server. SFTP is a secure way to transfer files, and this tool supports incremental uploads, private-key binding, and permission fixes.
memory
Retrieve relevant durable BB memories or save verified knowledge useful to future threads.
thread-list
Inspect or change the sidebar thread list's layout preferences: organization mode, sort, section order, hidden groups, collapsed groups, and thread row actions.
workflows
Author or run durable BB workflows when the user requests workflow execution or multi-agent orchestration.
jk
Manage Jenkins controllers with jk, including jobs, runs, logs, artifacts, credentials, nodes, queues, and plugins.
url
Fetch and extract text from web URLs.