Borrowing it
Nothing to install: this file belongs to mefos-lab/sift. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mefos-lab/sift/main/.claude/skills/investigate/SKILL.mdgit clone --depth 1 https://github.com/mefos-lab/siftWrote 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/mefos-lab/sift/investigate)<a href="https://agentmods.dev/skills/mefos-lab/sift/investigate"><img src="https://agentmods.dev/badge/skills/mefos-lab/sift/investigate/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/mefos-lab/sift/investigate"><img src="https://agentmods.dev/badge/skills/mefos-lab/sift/investigate.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00028 | $0.13023 |
| Opus 5.5 | $0.00011 | $0.05209 |
| Sonnet 5.5 | $0.00006 | $0.02605 |
| Haiku 4.5 | $0.00003 | $0.01302 |
Grade A, and why
investigate 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 2mo 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 — 1,409 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigate
The unified investigation skill. Searches ICIJ Offshore Leaks and OpenSanctions, cross-references findings, detects patterns, and produces structured intelligence reports.
Before running, load patterns/INDEX.yaml from the project root.
Usage
/investigate <name> — full cross-reference (default)
/investigate <name> --trace — network traversal (2 hops)
/investigate <name> --trace --depth 3 — deep network walk (3 hops)
/investigate <name> --patterns — structural pattern analysis
/investigate <name> --compliance — rigorous sanctions/PEP screening
/investigate <name> --compliance --dob 1970-05-15 --nationality RU
/investigate <name> --monitor — new sanctions since 30 days
/investigate <name> --monitor --since 2026-01-01
/investigate <name> --jurisdiction — jurisdictional footprint
/investigate <name1>, <name2> — compare connections
/investigate <name1>, <name2>, <name3>, ... — batch exposure screening
/investigate --scan <pattern> — exploratory pattern hunt (no target)
/investigate --scan all — run all 14 scan types
/investigate <name> --scan <pattern> — targeted investigation + focused scan
Valid scan types: sanctions-evasion, pep-opacity, nominee-shield,
mass-registration, intermediary-cluster, rapid-dissolution,
llp-opacity, beneficial-ownership-gap
When no flag is given, the default mode is a full cross-reference investigation (the most comprehensive single-name analysis).
For --scan mode, see the dedicated section at the end.
Shared procedure (all targeted modes)
These steps run for all modes that have a target name. The --scan
mode (standalone, no target) has its own procedure — see below.
Step 1: Deep traversal + independent searches (parallel)
Launch all of the following in parallel — they are independent:
1a. deep_trace — cross-source network traversal:
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.
- 2mo ago First seen · 1,409 lines · 28 tokens per session scan A 1ec9f1fe2b75
investigate is a skill published in the GitHub repository mefos-lab/sift (6 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 13,023 once invoked, about $0.0001 per session on Opus 5.5. 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.
investigate compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| investigatemefos-lab/sift | Skill | 6 | 2mo ago | MIT | A | 28 | Claude Code |
| fto-triageanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 81 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| specification-writingwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 49 | Claude Code |
| terms-of-servicegenspark-ai/genoffice | Skill | 12k | 2d ago | Apache-2.0 | A | 32 | Claude Code, Codex |
| x-scorecardx-cmd/x-cmd | Skill | 4.7k | 7d ago | Apache-2.0 | A | 57 | Claude Code, Codex |
| gesellschaftsrechtliche-satzungen-agbKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 69 | Claude Code |