OpenParable
Skip to content
← Back to skills

Osgrep

Development
osgrep

Osgrep is an Agent Skill for development published in the Ryandonofrio3/osgrep repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Semantic code search. Use alongside grep - grep for exact strings, osgrep for concepts.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/Ryandonofrio3/osgrep/blob/HEAD/plugins/osgrep/skills/osgrep/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/osgrep, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

What osgrep does

Finds code by meaning. When you'd ask a colleague "where do we handle auth?", use osgrep.

  • grep/ripgrep: exact string match, fast
  • osgrep: concept match, finds code you couldn't grep for

Primary command

osgrep "where do we validate user permissions"

Returns ~10 results with code snippets (15+ lines each). Usually enough to understand what's happening.

Output explained

ORCHESTRATION src/auth/handler.ts:45
Defines: handleAuth | Calls: validate, checkRole, respond | Score: .94

export async function handleAuth(req: Request) {
  const token = req.headers.get("Authorization");
  const claims = await validateToken(token);
  if (!claims) return unauthorized();
  const allowed = await checkRole(claims.role, req.path);
  ...
  • ORCHESTRATION = contains logic, coordinates other code
  • DEFINITION = types, interfaces, classes
  • Score = relevance (1 = best match)
  • Calls = what this code calls (helps you trace flow)

When to Read more

The snippet often has enough context. But if you need more:

# osgrep found src/auth/handler.ts:45-90 as ORCH
Read src/auth/handler.ts:45-120

Read the specific line range, not the whole file.

Other commands

# Trace call graph (who calls X, what X calls)
osgrep trace handleAuth

# Skeleton of a huge file (to find which ranges to read)
osgrep skeleton src/giant-2000-line-file.ts

# Just file paths when you only need locations
osgrep "authentication" --compact

Workflow: architecture questions

# 1. Find entry points
osgrep "where do requests enter the server"
# Review the ORCH results - code is shown

# 2. If you need deeper context on a specific function
Read src/server/handler.ts:45-120

# 3. Trace to understand call flow
osgrep trace handleRequest

Tips

  • More words = better results. "auth" is vague. "where does the server validate JWT tokens" is specific.
  • ORCH results contain the logic - prioritize these
  • Don't read entire files. Use the line ranges osgrep gives you.
  • If results seem off, rephrase your query like you'd ask a teammate

If Index is Building

If you see "Indexing" or "Syncing": STOP. Tell the user the index is building. Ask if they want to wait or proceed with partial results.