project-code

A command for managing a searchable index of a project's code. The index can store functions, classes, methods, names, code text, and—in some setups—semantic search vectors.

In plain words
What is it for?
Use it to check the index, initialize or synchronize it, search code, find symbols, list indexed files, and inspect project documentation.
Why use it?
It gives the agent a faster way to find relevant code and symbols in a large project. It also keeps code search separate from session notes and decisions.

Command

Install

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.

agentmods
npx agentmods add commands/adilkalam/orca/project-code
Clone the repo
git clone --depth 1 https://github.com/adilkalam/orca
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,283 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.01283
Opus 5 $0.00011 $0.00642
Sonnet 5 $0.00004 $0.00257
Haiku 4.5 $0.00002 $0.00128

Measured yesterday against content hash ef082a53f8e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-code 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 yesterday.

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.

commands/project-code.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Context Management (code-index.db)

Parse the user's command to determine which action to take:

Command: /project-code $ARGUMENTS

What is code-index.db?

code-index.db stores code intelligence for your project:

  • Code chunks - Functions, classes, methods with their code
  • Symbols - Extracted function/class names for fast lookup
  • Embeddings - Semantic vectors for similarity search (when enabled)

This is separate from Workshop (session memory for decisions/gotchas).

Subcommand Routing

1. Status (default, no args, or status)

Trigger: /project-code or /project-code status

Show code-index.db status:

if [ -f ".claude/memory/code-index.db" ]; then
    echo "code-index.db: .claude/memory/code-index.db"
    python3 ~/.claude/scripts/code-index.py status
else
    echo "code-index.db: Not initialized"
    echo ""
    echo "Run: /project-code sync"
fi

2. Sync Code (sync)

Trigger: /project-code sync

Index/sync code into code-index.db:

python3 ~/.claude/scripts/code-index.py sync

Show the sync results. If it's the first sync, this will create the database.


3. Initialize (init)

Trigger: /project-code init

Initialize code-index.db (same as sync but explicit):

python3 ~/.claude/scripts/code-index.py init

4. Hybrid Search (search <query>)

Trigger: /project-code search <query>

Search code using hybrid search (semantic + symbol + fulltext):

python3 ~/.claude/scripts/code-index.py hsearch "<query>" --limit 10

Display results clearly with file paths, symbol names, and relevance scores.


5. Symbol Search (symbol <name>)

Trigger: /project-code symbol <name>

Fast lookup by function/class name:

python3 ~/.claude/scripts/code-index.py symbol "<name>" --limit 10

6. Find Files (files <pattern>)

Trigger: /project-code files <pattern>

Search for files matching a pattern in the index:

Read the full file on GitHub · 185 lines

Changes

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.

  1. yesterday First seen · 185 lines · 22 tokens per session scan A ef082a53f8e5

Subscribe to this mod's changes

project-code is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,283 once invoked, about $0.0001 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 2026-08-31.