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 soxoj/claude-osint-deploy --skill osint-deploygit clone --depth 1 https://github.com/soxoj/claude-osint-deployWrote 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/soxoj/claude-osint-deploy/osint-deploy)<a href="https://agentmods.dev/skills/soxoj/claude-osint-deploy/osint-deploy"><img src="https://agentmods.dev/badge/skills/soxoj/claude-osint-deploy/osint-deploy.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 | $0.00175 | $0.06638 |
| Opus 5 | $0.00088 | $0.03319 |
| Sonnet 5 | $0.00035 | $0.01328 |
| Haiku 4.5 | $0.00017 | $0.00664 |
Grade B, and why
osint-deploy scanned grade B with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
**Never** `pip install` into the system interpreter, never `sudo pip`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
the install, `curl` the endpoint it scrapes and look for a challenge/redirect. How it starts
The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OSINT tool deploy & verify
Goal: the tool is installed, isolated, and proven to run on this machine — not "the install command exited 0".
Non-negotiable: never report success without Phase 5 evidence. OSINT tools rot fast (dead APIs,
stale pins, abandoned repos). A green pip install means nothing.
Scope
Deploy/verify tooling only. Run tools against targets the user is authorised to investigate, use documented example targets for verification, keep verification to a single low-volume request, and honour each tool's rate limits and the target's ToS. Report which sources need API keys instead of hunting for ways around them.
Phase 0 — Environment (once per machine)
python3 scripts/env_probe.py # or: py scripts/env_probe.py on Windows
Cache the output in the conversation; it decides everything below. If python3 itself is missing,
read references/stacks.md § Bootstrap.
Phase 1 — Recon the repo (never guess)
One command clones the repo and prints every fact below:
python3 scripts/recon.py <owner/repo> # clones into ~/osint_tools/src/<repo>
It reports stars/last-commit/archived, entry points, manifest files, the CI matrix and CI's own test
commands, requires-python/go/node engines, system packages, API keys named in the README,
release assets, Docker files, test dirs, and the README's example invocations. Read the CI section
first. Fall back to reading by hand only for what it flags as missing:
| Read | What you get |
|---|---|
.github/workflows/*.yml |
The ground truth: supported OS matrix, Python/Go/Node versions, system packages, the exact test command. Read this before anything else. |
README* |
Install commands, example invocations with expected output (Phase 5 T2 material), required API keys |
pyproject.toml / setup.py / requirements*.txt |
requires-python, deps, entry points |
go.mod / package.json / Cargo.toml |
Toolchain version |
Dockerfile, docker-compose.yml |
An official, pre-solved dependency set |
Releases / tags via gh release list or the API |
Prebuilt binaries → zero toolchain |
| Last commit date, open issues | Abandoned repo? Expect stale pins; jump to a pinned interpreter or Docker early |
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.
- examples/ghunt.checks.json 461 B
- examples/interactive-cli.checks.json 1.4 KB
- examples/sherlock.checks.json 783 B
- examples/theharvester.checks.json 1.8 KB
- examples/web-check.checks.json 650 B
- references/known-tools.md 16 KB
- references/stacks.md 4.5 KB
- references/troubleshooting.md 9.6 KB
- references/verify.md 5.4 KB
- scripts/env_probe.py 2.4 KB runs code
- scripts/recon.py 8.7 KB runs code
- scripts/verify.py 3.3 KB runs code
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 · 332 lines · 175 tokens per session scan B a5f0de89ab2a
osint-deploy is a skill published in the GitHub repository soxoj/claude-osint-deploy (12 stars, last pushed 10d ago), licensed MIT. It adds 175 tokens to every session and 6,638 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
create-kr-patch
Use for Korean (Hangul) fan translations of retro console or PC games, including ROM or disc analysis, text-engine reverse engineering, Hangul fonts and custom encodings, script extraction and reinsertion, code hooks, reproducible product builds, and emulator verification. Apply it to new investigations and follow-up…
0xarchive
Query historical and real-time crypto market data from 0xArchive across two top-level venue APIs: Hyperliquid and Lighter.xyz. HIP-3 builder perps live under the Hyperliquid namespace at /v1/hyperliquid/hip3. HIP-4 outcome markets (binary prediction markets like 'Will BTC be >= X by date Y?') live at…
make-brief
Produce a local HTML page a human can actually read and decide from - a narrative decision brief, an item-by-item technical review page, or a mechanism explainer that walks through a system and its terminology. Triggers when the user says "write this up as an HTML page for me", "I don't follow, give me the full…
quiz-me
Quiz the user on root cause and intended fix BEFORE writing any non-trivial code, then verify comprehension of every change after. Use when the user asks for a bug fix, refactor, or feature and wants to stay technically sharp instead of vibe-coding. Also use when the user says "quiz me", "don't let me vibe code", or…
slopmop
Trigger when you would normally reach for pytest, gh, mypy, black, or other raw repo tooling. Redirect to sm swab, sm scour, sm buff, sm sail, sm refit, or sm doctor so remediation follows the established rails. Also trigger when asked to "install" or "set up" slop-mop in a repo, or when you find a repo with sm…
markup-mode
Add a frontend-only review/markup layer to any HTML artifact, Markdown document, or live UI so a reviewer can anchor comments to specific text or specific elements, then compile them into tagged Markdown for an agent to act on. Use when the user wants to "mark up this page", "add a review/comment layer", "annotate…