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 jaredlangleycc/nightshift-os --skill icp-discoverygit clone --depth 1 https://github.com/jaredlangleycc/nightshift-osWrote 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/jaredlangleycc/nightshift-os/icp-discovery)<a href="https://agentmods.dev/skills/jaredlangleycc/nightshift-os/icp-discovery"><img src="https://agentmods.dev/badge/skills/jaredlangleycc/nightshift-os/icp-discovery.svg" alt="Measured on agentmods" 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 | $0.00176 | $0.04611 |
| Opus 5 | $0.00088 | $0.02305 |
| Sonnet 5 | $0.00035 | $0.00922 |
| Haiku 4.5 | $0.00018 | $0.00461 |
Grade A, and why
icp-discovery 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 8d 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 — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ICP Discovery
The skill that turns a vague "small business owners" into a precise "B2B SaaS sales managers, under 18 months in role, 50-500 employees, who own a number but did not own one before." Without that precision, positioning is vague, copy is vague, outreach is vague, and the user spends hours per week talking to fits they will never close.
This skill works whether you have zero customers or 50. The depth changes with stage. The discipline does not.
When this skill triggers
- "Define my ICP"
- "Who buys from me"
- "Ideal customer profile"
- "Ideal client"
- "Who should I sell to"
- "Customer research"
- "Who is my customer"
- "Narrow my niche"
- "I keep getting unfit leads"
- "My pipeline is full but nothing closes"
- "I want fewer but better clients"
- Auto-activated when assessment Section 6 (Offer + ICP) is filled with vague answers like "small businesses" or "anyone who needs marketing help"
- Auto-activated when assessment Goal Section 9 contains "narrow my niche" or "find my customer"
NOT for: positioning statement work (use positioning). NOT for: pricing or packaging (use pricing-strategy, offer-design). NOT for: building a prospect list at volume (use outreach-drafter after ICP locks).
What an ICP is and is not
An ICP is the precise definition of who you sell to. It is more specific than a target market. It is the entry where a sales motion, a pricing decision, a copy decision, or an offer change can be validated.
An ICP is:
- One specific stage of company (e.g., "Series A to B, 50-500 employees, B2B SaaS")
- One specific role (e.g., "Sales Manager, not VP of Sales, not Director")
- One specific situation (e.g., "under 18 months in the role, first-time manager")
- One specific pain (e.g., "missed quota two quarters in a row, blamed reps, knows the issue is them")
- One specific buying trigger (e.g., "boss said get coaching or get replaced")
An ICP is NOT:
- A target market ("B2B SaaS companies" is a market; "Sales Managers <18mo at B2B SaaS 50-500" is an ICP)
- A persona built from imagination ("Sarah is a busy mom and a hard worker" is not an ICP)
- A list of people who might buy (this is a TAM exercise)
- Three different customer types (you cannot serve three ICPs at once until $25K+ MRR)
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 444 lines · 0 tokens per session scan A f5dd86c8a57e
icp-discovery is a skill published in the GitHub repository jaredlangleycc/nightshift-os (3 stars, last pushed 1mo ago), licensed MIT. It adds 176 tokens to every session and 4,611 once invoked, about $0.0009 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 skills, from other repositories
Brand Guidelines Generator
Create and maintain brand style guides for consistent visual identity.
web-vid
Turn a web app or marketing site into a recreated (not screen-recorded) Remotion promo video — pixel-faithful to the site's own design system, choreographed clicks/scrolls/zooms, rendered to MP4. Use when the user asks for a product demo video, a promo/teaser for LinkedIn or social, an "walkthrough video" of their…
pitchdocs
Generate marketing-quality repository documentation from codebase analysis. Scans 10 signal categories, extracts features with file-level evidence, and produces README, CHANGELOG, ROADMAP, and 15+ more docs. Zero runtime dependencies. For AI context file management, see ContextDocs.
demo-video-factory
Generate a custom 26s product-demo video from any SaaS URL — brand-matched scenes, a recreated product-UI "wow" scene, real screenshots, and a soundtrack. Use whenever the user wants a demo, promo, launch, or marketing video for a website or product.
brand
Brand context management for marketing sessions with continuity across conversations.
liking-factor-engineer
Analyze and engineer liking to increase rapport, persuasion, and compliance in marketing, sales, and communication contexts. Use this skill when the user wants to improve how much an audience likes them, their brand, or their message — including writing sales copy, designing onboarding flows, crafting brand voice…