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 tdimino/bg3se-macos --skill osgrep-referencegit clone --depth 1 https://github.com/tdimino/bg3se-macosWrote 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/tdimino/bg3se-macos/osgrep-reference)<a href="https://agentmods.dev/skills/tdimino/bg3se-macos/osgrep-reference"><img src="https://agentmods.dev/badge/skills/tdimino/bg3se-macos/osgrep-reference/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/tdimino/bg3se-macos/osgrep-reference"><img src="https://agentmods.dev/badge/skills/tdimino/bg3se-macos/osgrep-reference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 11 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
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 | $0.00052 | $0.02431 |
| Opus 5 | $0.00026 | $0.01215 |
| Sonnet 5 | $0.00010 | $0.00486 |
| Haiku 4.5 | $0.00005 | $0.00243 |
Grade A, and why
osgrep-reference 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 9d 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
osgrep: Semantic Code Search
ALWAYS prefer osgrep over grep/rg for code exploration. It finds concepts, not just strings.
Overview
osgrep is a natural-language semantic code search tool that finds code by concept rather than keyword matching. Unlike grep which matches literal strings, osgrep understands code semantics using local AI embeddings.
Version 0.5.16 (Dec 2025) highlights:
skeletoncommand: Compress files to function/class signatures (~85% token reduction)tracecommand: Show who calls/what calls for any symbol (call graph)symbolscommand: List all indexed symbols with definitionsdoctorcommand: Health/integrity verificationlistcommand: Display all indexed repositories- Per-project
.osgrep/directories (no longer global~/.osgrep/data) - V2 architecture with improved performance (~20% token savings, ~30% speedup)
- Go language support
--resetflag for clean re-indexing- ColBERT reranking for better result relevance
- Role detection: distinguishes orchestration logic from type definitions
- Split searching: separate "Code" and "Docs" indices
When to use osgrep:
- Exploring unfamiliar codebases ("where is the auth logic?")
- Finding conceptual patterns ("show me error handling")
- Locating cross-cutting concerns ("all database migrations")
- User explicitly asks to search code semantically
When to use traditional tools:
- Searching for exact strings or identifiers (use
Grep) - Finding files by name pattern (use
Glob) - Already know the exact location (use
Read)
Quick Start
IMPORTANT: You must cd into the project directory before running osgrep commands.
osgrep uses per-project .osgrep/ indexes, so it only searches the repo you're currently in.
cd /path/to/project # REQUIRED: cd into the project first
osgrep "your query" # Now search works
Basic Search
osgrep "your semantic query"
osgrep search "your query" path/to/scope # Scope to subdirectory
osgrep skeleton src/file.py # Compress file to signatures
osgrep trace functionName # Show call graph
osgrep symbols # List all symbols
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.
- 9d ago First seen · 330 lines · 52 tokens per session scan A 47f2c5e8604b
osgrep-reference is a skill published in the GitHub repository tdimino/bg3se-macos (57 stars, last pushed 28d ago), licensed MIT. It adds 52 tokens to every session and 2,431 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.
Other skills, from other repositories
ctf-rev
Solve CTF reverse engineering challenges using systematic analysis to find flags, keys, or passwords. Use for crackmes, binary bombs, key validators, obfuscated code, algorithm recovery, or any challenge requiring program comprehension to extract hidden information.
deep-analysis
Performs focused, depth-first investigation of specific reverse engineering questions through iterative analysis and database improvement. Answers questions like "What does this function do?", "Does this use crypto?", "What's the C2 address?", "Fix types in this function". Makes incremental improvements (renaming…
pyghidra-scripting
Write and run Python (PyGhidra) code inside the Ghidra session that ReVa's MCP server is already attached to, using the five ReVa scripting tools — run-script, list-scripts, read-script, write-script, edit-script. Use this whenever the user asks to execute Python against the current program, reach for the Ghidra Flat…
binary-triage
Performs initial binary triage by surveying memory layout, strings, imports/exports, and functions to quickly understand what a binary does and identify suspicious behavior. Use when first examining a binary, when user asks to triage/survey/analyze a program, or wants an overview before deeper reverse engineering.
reverse-engineering-company-system
Run reverse engineering as a coordinated EVOKORE operating system with expert panels, additive workflows, and lightweight learning loops. Use when the target is complex enough that you want more than isolated tool calls.
reverse-engineering-workbench
Coordinate EVOKORE reverse-engineering work across Ghidra-style static analysis, semantic recovery, and debugger-guided triage. Use when opening an unfamiliar binary, planning a decompilation workflow, or choosing between static and dynamic analysis paths.