search-threads

search-threads is a skill for Claude Code, Codex from mostlyharmless-ai/watercooler. It costs 35 tokens per session (1,020 once invoked), scanned A, original, Apache-2.0.

A skill for searching recorded project discussions with filters for roles, entry types, dates, threads, status, and agents.

In plain words
What is it for?
Use it to locate plans, decisions, notes, reviews, or closures by topic, date, thread, role, status, or agent.
Why use it?
It helps find past decisions and notes without manually reading every discussion, while supporting exact filter combinations and broader matching.

Skill for Claude CodeCodex

Part of the watercooler plugin — 7 skills, 1 MCP server shipped together

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/mostlyharmless-ai/watercooler/search-threads
Any agent
npx skills add mostlyharmless-ai/watercooler --skill search-threads
Clone the repo
git clone --depth 1 https://github.com/mostlyharmless-ai/watercooler

Made for: Claude Code, Codex.

Or install watercooler, the plugin that ships this one along with the rest of its 7 skills, 1 MCP server.

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.

agentmods badge for search-threads

README.md
[![agentmods](https://agentmods.dev/badge/skills/mostlyharmless-ai/watercooler/search-threads.svg)](https://agentmods.dev/skills/mostlyharmless-ai/watercooler/search-threads)
Your own site
<a href="https://agentmods.dev/skills/mostlyharmless-ai/watercooler/search-threads"><img src="https://agentmods.dev/badge/skills/mostlyharmless-ai/watercooler/search-threads.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,020 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 $0.00035 $0.01020
Opus 5 $0.00017 $0.00510
Sonnet 5 $0.00007 $0.00204
Haiku 4.5 $0.00003 $0.00102

Measured 5d ago against content hash 1d963e4bbe39, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

search-threads 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 5d 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.

plugins/claude/watercooler/skills/search-threads/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Search Threads with Filters

Search: $ARGUMENTS

Filter Syntax

Parse these filters from arguments:

  • role:X - Filter by role (planner, implementer, critic, tester, pm, scribe)
  • type:X - Filter by entry type (Note, Plan, Decision, PR, Closure)
  • after:DATE / before:DATE - Time range (ISO format: 2024-01-15)
  • thread:X - Specific thread topic
  • status:X - Thread status (OPEN, CLOSED)
  • agent:X - Filter by agent name
  • or: (flag, no value) - Use OR token matching instead of AND (see below)
  • Remaining text becomes the search query

Token matching default is AND. Multi-keyword queries like "decided committed resolved" require ALL tokens present in the same entry — this often returns 0 hits. Add or: to use OR matching: any token qualifies. Use or: whenever searching for any of several keywords.

Parsing Rules

  1. Split $ARGUMENTS on whitespace into tokens
  2. A token is a filter if it matches ^(role|type|after|before|thread|status|agent):[^\s]+$
  3. The or: token (no value) sets query_operator="OR" — consume it as a flag, not query text
  4. The filter key is everything before the first :, the value is everything after
  5. All non-filter tokens are joined with spaces to form the query text

Edge Cases

  • role:planner:advanced → key=role, value=planner:advanced (first colon splits)
  • Multiple values for same key → last one wins
  • Empty value (role:) → ignore, treat entire token as query text
  • No query text → search with filters only (empty query string)

Steps

  1. Parse arguments into filters and query text using rules above.

  2. Load MCP tool:

    ToolSearch: select:mcp__watercooler__watercooler_search
    
  3. Execute search with parsed query and filters. Pass each filter as its own named parameter — omit any filter param that was not explicitly parsed from the arguments. Do NOT use a filters={} dict (no such parameter exists):

    # Example: only role was given
    mcp__watercooler__watercooler_search(
      query="config", mode="entries", role="planner"
    )
    # Example: multiple filters
    mcp__watercooler__watercooler_search(
      query="", mode="entries", role="planner", entry_type="Decision"
    )
    # Example: thread + status filters
    mcp__watercooler__watercooler_search(
      query="", mode="entries", thread_topic="mcp-migration", thread_status="OPEN"
    )
    # Example: no filters, just query text
    mcp__watercooler__watercooler_search(
      query="config migration", mode="entries"
    )
    # Example: OR mode — any of several keywords (use when or: flag is set)
    mcp__watercooler__watercooler_search(
      query="decided resolved committed opted agreed chosen",
      query_operator="OR", mode="entries"
    )
    

Read the full file on GitHub · 105 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. 5d ago First seen · 105 lines · 35 tokens per session scan A 1d963e4bbe39

Subscribe to this mod's changes

search-threads is a skill published in the GitHub repository mostlyharmless-ai/watercooler (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,020 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.