agentmods.dev

intel-collector

intel-collector is a skill for Claude Code, Codex from Szotasz/marveen. It costs 56 tokens per session (1,265 once invoked), scanned A, original, MIT.

A template for an hourly information-gathering job focused on topics you define. It stores relevant findings in an intelligence database used by a daily briefing.

In plain words
What is it for?
Use it to search selected sources, screen findings for important numbers or deadlines, save relevant records, and send Telegram only for events that cross your chosen alert threshold.
Why use it?
It keeps routine monitoring separate from urgent notifications. The template is disabled by default and requires replacing its placeholder topics before use.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 98repo today A scan SkillSpector: pass 56 tokens original MIT

Good fit Use it to search selected sources, screen findings for important numbers or deadlines, save relevant records, and send Telegram only for events that cross your chosen alert threshold.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/szotasz/marveen/intel-collector
View source ↗ Szotasz/marveen
Install

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.

Any agent
npx skills add Szotasz/marveen --skill intel-collector
Clone the repo
git clone --depth 1 https://github.com/Szotasz/marveen

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for intel-collector

README.md
[![agentmods](https://agentmods.dev/badge/skills/szotasz/marveen/intel-collector/github.svg)](https://agentmods.dev/skills/szotasz/marveen/intel-collector)
Your own site
<a href="https://agentmods.dev/skills/szotasz/marveen/intel-collector"><img src="https://agentmods.dev/badge/skills/szotasz/marveen/intel-collector/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.

agentmods 80×15 button for intel-collector

Your own site · 80×15
<a href="https://agentmods.dev/skills/szotasz/marveen/intel-collector"><img src="https://agentmods.dev/badge/skills/szotasz/marveen/intel-collector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,265 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.01265
Opus 5 $0.00028 $0.00633
Sonnet 5 $0.00011 $0.00253
Haiku 4.5 $0.00006 $0.00127

Measured 12d ago against content hash 6c8cc08053a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

intel-collector 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 12d 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.

seed-scheduled-tasks/intel-collector/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Proaktív hírszerző -- óránkénti gyűjtő ciklus

⚠️ SABLON: alapból KIKAPCSOLVA érkezik (task-config.json: "enabled": false). Mielőtt bekapcsolod, cseréld le az alábbi DOMAIN blokkokat a SAJÁT figyelt témáidra. A "FUTÁS VÉGE" szakasz (registry-írás) a rendszer fix része, azt ne vedd ki -- az táplálja a napi briefet.

Cél: a megadott domainek átfésülése, és MINDEN releváns találat beírása a registry-be. CSAK akkor küldj Telegram üzenetet a tulajdonosnak ({{OWNER_NAME}}), ha riasztás-szintű esemény van (általad definiált küszöb átlépése, sürgős határidő). Egyébként csendes futás: registry + napi napló.

DOMAIN 1 -- [CSERÉLD LE: pl. iparági hírek / versenytársak]

  1. WebSearch query-k (2-4 darab, a te témádra szabva):

    • "[KULCSSZÓ 1] 2026" site:[MEGBÍZHATÓ FORRÁS]
    • "[VERSENYTÁRS NÉV]" (legfrissebb hír)

  2. Minden találatnál rövid triage: tartalmaz-e számszerű adatot, bejelentést, határidőt ami a tulajdonost érinti? Ha van helyi LLM (Ollama MCP), az előszűrést delegálhatod oda IGEN/NEM formátumban -- token-takarékos.

  3. Csak a releváns rekordokat dolgozd fel. Ha a saját küszöbödet átlépi (pl. >X% árelmozdulás) -> Telegram értesítés.

DOMAIN 2 -- [CSERÉLD LE: pl. árfolyamok / piaci adatok]

  1. WebFetch [HIVATALOS FORRÁS URL, pl. jegybanki árfolyamoldal] Sáv-trigger példa: ha az érték a [ALSÓ]..[FELSŐ] sávon kívül van -> AZONNALI Telegram.

  2. Ritkább ellenőrzések időkapuval (pl. csak 09:00-kor, csak hétfőn, csak a hónap 1-jén): így az óránkénti futás olcsó marad. Első lépésként date Bash paranccsal nézd meg a pontos időt.

DOMAIN 3 -- [CSERÉLD LE: pl. jogszabály / pályázat / határidők -- vagy töröld]

  1. WebFetch [FORRÁS URL] Triage: van-e új kör / új határidő? Ha IGEN -> Telegram.

FUTÁS VÉGE (fix rész -- ez táplálja a napi briefet)

  1. REGISTRY-ÍRÁS (kötelező): MINDEN releváns találatot írj be a known_facts_registry-be a CLI-vel: 
    python3 {{INSTALL_DIR}}/scripts/intel_db.py add-fact \
  --title "RÖVID CÍM" --domain <a-te-domain-sluggod> \
  --source "URL vagy forrásnév" --tier <1|2|3> \
  --content "A tény tömör tartalma számokkal" --priority <0.0-1.0>
    • Az --id-t NE add meg: a CLI determinista id-t generál (domain-YYYYMMDD-hash8), így az óránkénti ismételt találat update lesz, nem duplikátum.
    • "DUPLICATE content already in registry" kimenet = már ismert tény, rendben, lépj tovább.
    • priority ökölszabály: riasztás-szintű trigger = 0.9; számszerű adat vagy határidő = 0.7; egyéb releváns = 0.5. Tier-1 forrás: +0.1, tier-3: -0.1 (0..1 közé vágva).
    • Ha egy KORÁBBI tény fejlődött tovább (ugyanaz a téma új számmal), ugyanazzal az --id-vel írd felül és --status evolving.
  2. Új követendő irány (még nem tény, de figyelni érdemes): add-watch: 
    python3 {{INSTALL_DIR}}/scripts/intel_db.py add-watch \
  --title "MIT" --domain <domain> --direction "MERRE mozdulhat" --notes "MIÉRT"
  3. POST /api/daily-log (agent_id: {{MAIN_AGENT_ID}}) -- mi futott, hány fact került a registry-be, státusz.
  4. Ha nincs riasztás: csend (a registry-írás NEM riasztás, arról nem megy Telegram).
  5. Ha riasztás: Telegram a tulajdonosnak, tömören, actionable formában.

Read the full file on GitHub · 72 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 12d ago First seen · 72 lines · 56 tokens per session scan A 6c8cc08053a0

Subscribe to this mod's changes

intel-collector is a skill published in the GitHub repository Szotasz/marveen (98 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 1,265 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 2026-08-30.

Claude CodeMulti-AgentResearchagent-harnessai-agentsai-assistantself-hosted
Related

Other skills, from other repositories

commonly

You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…

Team-Commonly/commonly · 0 tokens

oma-image

Multi-vendor AI image generation with authentication-aware parallel dispatch. Routes to Codex (gpt-image-2 via ChatGPT OAuth), Antigravity (Gemini-family "nano-banana" image models via agy CLI + Gemini Code Assist; exact model chosen internally by agy), and Pollinations (flux/zimage, free with signup). Use for image…

first-fluke/oh-my-agent · 90 tokens

oma-design

AI design specialist skill with DESIGN.md management, anti-pattern enforcement, optional Stitch MCP integration, and component library guidance. Covers typography, color systems, motion design (motion/react, GSAP, Three.js), responsive-first layouts, and accessibility (WCAG 2.2).

first-fluke/oh-my-agent · 58 tokens

oma-observability

Intent-based observability + traceability router across layers, boundaries, and signals. Routes to vendor-specific skills via category taxonomy; owns transport tuning, meta-observability, incident forensics. Use for observability, traceability, telemetry, APM, RUM, metrics, logs, traces, profiles, SLO, incident…

first-fluke/oh-my-agent · 78 tokens

oma-scholar

Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…

first-fluke/oh-my-agent · 73 tokens

officecli-commonly-templates

Use this skill when producing a polished, Commonly-branded deliverable (.docx brief / memo, .xlsx data matrix, .pptx deck) and you do not have specific brand guidance from the user. Trigger on: 'write me a brief', 'one-pager', 'memo', 'data sheet', 'status matrix', 'short deck', 'summary deck', 'closing slide', 'final…

Team-Commonly/commonly · 182 tokens