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 skills/noticedso/cli/noticed-searchnpx skills add noticedso/cli --skill noticed-searchgit clone --depth 1 https://github.com/noticedso/cliWhat 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 | $0.00051 | $0.00811 |
| Opus 5 | $0.00026 | $0.00405 |
| Sonnet 5 | $0.00010 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
noticed-search 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
noticed Search Skill
You have access to the noticed CLI for searching developer networks.
Available Commands
Search Network
noticed search "<query>" [options]
Options:
-l, --limit <n>— Maximum results (default 25, max 50)-o, --offset <n>— Pagination offset-s, --source <github|linkedin>— Filter by source--sort <col:dir>— Sort byname:asc,company:desc, etc.-p, --paths— Lazily fetch the shortest connection path to the top 5 hits-j, --json— Output JSON for further processing--no-color— Disable colors
Examples:
# Search by name
noticed search "Sarah Chen"
# Search by skill/topic
noticed search "AI engineers" --limit 10
# Search by company
noticed search "engineers at Google" --source github
# Get JSON output for processing (includes paths to top 5 hits)
noticed search "react developers" --json --paths
# Paginate results
noticed search "frontend" --offset 25 --limit 25
Find a Path
noticed path @sarahml # by GitHub login
noticed path 12345 # by github_user_id
noticed path --li sarah-chen # by LinkedIn username
noticed path @sarahml --json # machine-readable
Use this when you already know who you want to reach. The CLI resolves a login
by searching first, then calls the dedicated /api/search/path endpoint.
Configuration
# Mint an API key in the dashboard at /dashboard/api-keys, then:
noticed config --set-url https://your-instance.noticed.so
noticed config --set-key nk_live_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
# Show current config
noticed config --show
MCP Server (for AI agent integration)
# Start MCP server over stdio
noticed mcp
Environment Variables
The CLI reads credentials from:
- CLI flags (
--api-url,--api-key) - Environment variables (
NOTICED_API_URL,NOTICED_API_KEY) - Config file (
~/.config/noticed/config.json)
Search Tips
- Natural language: "AI engineers at startups", "frontend developers who know React"
- Names: "Sarah Chen", "John Smith" — searches both GitHub and LinkedIn
- Usernames: "@sarahml" — direct GitHub login lookup
- Companies: "Google", "Vercel" — matches company fields
- Skills/Topics: "kubernetes", "machine learning" — matches skills and repo topics
- Combined: Queries with 3+ words automatically validate extra words against company/headline
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 · 103 lines · 51 tokens per session scan A c6f8cfc737f1
noticed-search is a skill published in the GitHub repository noticedso/cli (0 stars, last pushed 10d ago), licensed MIT. It adds 51 tokens to every session and 811 once invoked, about $0.0003 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
purchasing
Create approved purchase orders with the create-purchase-order tool.
refunds
Check refund eligibility and use the refund-order tool safely.
document-service
This skill should be used when the user asks to "analyze this codebase", "document this service", "generate technical docs", "I inherited this code", "help me understand this system", "create docs for this project", "what does this system look like", "onboard me to this codebase", "this codebase has no docs"…
aws-step-functions
Build workflows with AWS Step Functions state machines using the JSONata query language. Covers Amazon States Language (ASL) structure, state types, variables, data transformation, error handling, AWS service integration, and migrating from the JSONPath to the JSONata query language.
hyperpod-version-checker
Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia), Python, and PyTorch. Use when checking component versions, verifying CUDA/driver compatibility, detecting version mismatches…
directory-management
Manages project directory setup and artifact organization. Use when starting a new project, resuming an existing one, or when a PLAN.md needs to be associated with a project directory. Creates the project folder structure (specs/, scripts/, notebooks/, manifests/, agentmemory/) and resolves project naming.