Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mishahanin/heading-osnpx agentmods add skills/mishahanin/heading-os/osintWrote 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/mishahanin/heading-os/osint)<a href="https://agentmods.dev/skills/mishahanin/heading-os/osint"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/osint/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/mishahanin/heading-os/osint"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/osint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00201 | $0.03744 |
| Opus 5 | $0.00101 | $0.01872 |
| Sonnet 5 | $0.00040 | $0.00749 |
| Haiku 4.5 | $0.00020 | $0.00374 |
Grade A, and why
osint 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OSINT - Open Source Intelligence
Master intelligence gathering skill. Produces executive-grade intelligence briefs on any target using parallel multi-source research, confidence-rated findings, and source attribution.
Variables
target: [Name of the company, person, market/region, or technology to investigate]
mode: company | person | market | technology - default: auto-detect from target
depth: standard | deep | maximum - default: deep
focus: [Optional - specific angle to emphasize, e.g., "financial health", "hiring signals", "regulatory exposure", "patent activity", "digital footprint"]
context: [Optional - why this intelligence is needed now, e.g., "pre-meeting", "due diligence", "competitive encounter", "partnership evaluation"]
Pre-flight: VPN Check (conditional, runs before Phase 0)
Apply reference/vpn-preflight.md before any network operation in this skill.
Some OSINT sources rate-limit datacenter and VPN exit IPs. Present the gate and
wait for explicit confirmation before any research stream reaches Google,
LinkedIn, or a public OSINT source. Skip it only for a target answered entirely
from datastore/, crm/, and context/.
Phase 0: Context Loading
Customization (optional). This skill is customization-aware (pilot). Resolve any per-exec overrides first: python scripts/resolve_customization.py --skill .claude/skills/osint. Apply any activation_steps_prepend, persistent_facts, and output-path overrides from the merged result. On any failure, proceed with the defaults below - never block. Layout + authoring guide: config/skill-custom/README.md.
Read before any research:
reference/search-domains.md- Domain filtering configuration (MANDATORY for all searches)context/strategy.md- Strategic priorities for 31C relevance framingcontext/pipeline.md- Active deals and investor conversationscontext/people.md- Key contacts and relationship contextcontext/business-info.md- ODUN.ONE capabilities, partner ecosystemdatastore/INDEX.md- Check if source documents exist for this target (especiallydatastore/intelligence/competitors/)
What ships with it
12 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.
- customize.toml 684 B
- evals/benchmark.json 2.0 KB
- evals/cases/case-1-protocol-commitment.json 539 B
- evals/cases/case-2-no-fabrication.json 545 B
- evals/cases/case-3-31c-relevance.json 544 B
- references/output-format.md 5.1 KB
- references/streams-company.md 3.3 KB
- references/streams-market.md 2.4 KB
- references/streams-person.md 2.0 KB
- references/streams-technology.md 1.8 KB
- tests.md 1.4 KB
- triggers.json 1.1 KB
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 · 266 lines · 201 tokens per session scan A e6b0db2ff4cc
osint is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 201 tokens to every session and 3,744 once invoked, about $0.0010 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 2026-09-03.
Other skills, from other repositories
shogun-bloom-config
An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
shogun-model-list
A reference table of AI command-line tools, their available models, subscription requirements, and maximum Bloom capability levels. Bloom's Taxonomy is a scale describing thinking tasks, from remembering information to creating new designs.
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
shogun-readme-sync
A skill that compares an English README with its Japanese counterpart and brings them back into alignment. A README is the project document that explains what the software is and how to use it.
shogun-agent-status
A skill that shows whether the agents in a multi-agent Japanese feudal-themed team are working, waiting, missing, or assigned tasks. It combines terminal session status, task files, and unread messages.