cas-search

A search tool for finding information, tasks, rules, skills, and code in a shared coding-agent knowledge base.

In plain words
What is it for?
Use it to search by meaning, find code symbols, match exact text with regular expressions, inspect context, and locate related tasks or stored learnings.
Why use it?
It helps you locate relevant context without checking every file or past record manually.

Skill for Claude CodeCodex

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 skills/codingagentsystem/cas/cas-search
Any agent
npx skills add codingagentsystem/cas --skill cas-search
Clone the repo
git clone --depth 1 https://github.com/codingagentsystem/cas

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 519 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 $0.00055 $0.00519
Opus 5 $0.00028 $0.00260
Sonnet 5 $0.00011 $0.00104
Haiku 4.5 $0.00006 $0.00052

Measured 2d ago against content hash 690b11390af3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cas-search 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 2d 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/cas-search/SKILL.md · 49 lines

What it actually says

Use mcp__cas__search to find information across CAS content and code. Choose the right action for the job:

Which Action to Use

search — Conceptual queries across memories, tasks, rules, skills:

mcp__cas__search action=search query="authentication flow" doc_type=entry

Filter with doc_type (entry, task, rule, skill, code_symbol, code_file) for better relevance.

code_search — Find code symbols by what they do, not exact names:

mcp__cas__search action=code_search query="user authentication" kind=function language=rust

Use include_source=true to get source code inline.

grep — Exact regex pattern matching in files:

mcp__cas__search action=grep pattern="TODO:" glob="*.rs"

Prefer the built-in Grep tool for simple patterns where you already know file paths.

Decision Guide

Need Action
"How does X work?" search or code_search
Find exact string or regex grep
Find past learnings search with doc_type=entry
Find function by concept code_search
Find related tasks search with doc_type=task

Other Actions

  • context — Session context summary: recent activity, active tasks, relevant memories
  • context_for_subagent — Task-focused context for spawning subagents (pass task_id and max_tokens)
  • observe — Record discoveries/decisions during work (observation_type: general, decision, bugfix, feature, refactor, discovery)
  • entity_list / entity_show — Browse extracted entities (person, project, technology, etc.)
  • code_show — Full details for a specific code symbol by ID
  • blame — Git blame with optional AI-line filtering (file_path, line_start, line_end)
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. 2d ago First seen · 49 lines · 55 tokens per session scan A 690b11390af3

Subscribe to this mod's changes

cas-search is a skill published in the GitHub repository codingagentsystem/cas (151 stars, last pushed 5mo ago), licensed MIT. It adds 55 tokens to every session and 519 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.