What is add-claude-context?

A deprecated skill for semantic code search, meaning search by the intent of a query rather than only matching exact words.

Do not use it as described; the supplied text says to use scripts/code_search.py for local semantic search instead.

It records an older approach that was found not to work and identifies a local replacement based on SQLite and Ollama.

add-claude-context — Skill for Claude Code by sliamh11

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.

Any agent

npx skills add sliamh11/Deus --skill add-claude-context

Clone the repo

git clone --depth 1 https://github.com/sliamh11/Deus

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sliamh11/deus/add-claude-context.svg)](https://agentmods.dev/skills/sliamh11/deus/add-claude-context)

Your own site

<a href="https://agentmods.dev/skills/sliamh11/deus/add-claude-context"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/add-claude-context.svg" alt="Measured on agentmods" height="20"></a>

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,651 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. ✓ AI security review Sonnet 5 · 6 Sept 2026 📄 Read the review Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 35 findings, up to high

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 →

high Agent Snooping · line 32
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
high Agent Snooping · line 32
Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
high Agent Snooping · line 32
Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
high Agent Snooping · line 297
Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
high Agent Snooping · line 326
Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
high Agent Snooping · line 421
Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
high Agent Snooping · line 433
Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
high Agent Snooping · line 439
Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
high Agent Snooping · line 466
Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
high Supply Chain · line 94
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
high Privilege Escalation · line 167
Potential security issue detected. Manual review is recommended.

Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
high Supply Chain · line 418
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
high Tool Misuse · line 486
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
high Tool Misuse · line 486
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
high Tool Misuse · line 494
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
high Tool Misuse · line 495
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
high Tool Misuse · line 501
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
medium MCP Rug Pull · line 9
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium Data Exfiltration · line 94
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
medium Rogue Agent · line 113
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00030	$0.05651
Opus 5	$0.00015	$0.02825
Sonnet 5	$0.00006	$0.01130
Haiku 4.5	$0.00003	$0.00565

Measured 8d ago against content hash 7a5133fec0bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

add-claude-context 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 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.

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.

.claude/skills/add-claude-context/SKILL.md · 531 lines

How it starts

The opening of the file, as written. The whole thing — 531 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Claude Context (Semantic Code Search) -- DEPRECATED

This skill is deprecated. claude-context (Milvus-based) was evaluated and found to have never worked due to 5 cascading bugs (wrong config path, corrupt npx cache, wrong protocol, broken network isolation, short timeout). Milvus is also massive overkill for code search at any realistic codebase scale.

Replacement: scripts/code_search.py -- native semantic code search using sqlite-vec + Ollama embeddings + RRF fusion, following the memory_tree.py pattern. No Docker, no Milvus, no external dependencies beyond Ollama.

The content below is preserved for historical reference only.

This skill adds semantic code search to Claude Code via the claude-context MCP server by Zilliz. Once installed, Claude can index any codebase and search it by meaning — not just keyword matching.

Tools added:

index_codebase — index a directory into the vector database
search_code — semantic search across indexed code
get_indexing_status — check indexing progress
clear_index — remove an index

Privacy: All data stays local. Embeddings via Ollama, vectors in a network-isolated Docker Milvus container. No cloud APIs, no telemetry. See Security for the full defense-in-depth breakdown.

Phase 1: Pre-flight

Check if already configured

grep -q "claude-context" ~/.claude/mcp.json 2>/dev/null && echo "INSTALLED" || echo "NOT_INSTALLED"

If already installed, skip to Phase 5 (Verify).

Check prerequisites

Docker:

docker info > /dev/null 2>&1 && echo "Docker OK" || echo "Docker not running"

If Docker is not running, tell the user to start Docker Desktop (macOS) or the Docker daemon (Linux).

Ollama:

ollama list > /dev/null 2>&1 && echo "Ollama OK" || echo "Ollama not running"

If Ollama is not installed, direct the user to https://ollama.com/download.

Node.js version:

node --version

Read the full file on GitHub · 531 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.

8d ago First seen · 531 lines · 30 tokens per session scan F 7a5133fec0bf

Subscribe to this mod's changes

add-claude-context is a skill published in the GitHub repository sliamh11/Deus (51 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 5,651 once invoked, about $0.0002 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.

Claude Code ai-assistant ai-memory persistent memory self-improving-ai semantic-memory

memcord

Privacy-first, self-hosted chat memory for OpenClaw — save and recall conversation history across sessions without any cloud dependency.

ukkit/memcord · 28 tokens

roadmap-build

Build or repair a roadmap that agents can actually execute, not just read. Produces a single validated YAML source of truth, generated views, definitions of done with evidence kinds, a task pool linked on two axes, an idea intake queue, and three standing checks that keep it honest. Use when asked to "build a…

datacore-one/datacore · 111 tokens

add-claude-context