threads

A workflow for listing and opening Watercooler discussion threads, which are project conversations organized by topic and status. It can show summaries, activity, and who currently needs to act.

In plain words
What is it for?
Use it to list open or closed threads, inspect a topic, review recent entries, and identify threads awaiting action.
Why use it?
Important decisions and follow-up tasks can be buried in many project discussions. Thread navigation makes active and relevant conversations easier to find.

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

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 564 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 $0.00028 $0.00564
Opus 5 $0.00014 $0.00282
Sonnet 5 $0.00006 $0.00113
Haiku 4.5 $0.00003 $0.00056

Measured 2d ago against content hash 9e5d54c6556a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

plugins/claude/watercooler/skills/threads/SKILL.md · 76 lines

What it actually says

List and Navigate Threads

Arguments: $ARGUMENTS

Modes

  • No arguments: List all threads grouped by status
  • open or closed: Filter by status
  • <topic>: Show specific thread details
  • --raw: Show full JSON response

Steps

Mode 1: List All Threads (no arguments or status filter)

  1. Load tool:

    ToolSearch: select:mcp__watercooler__watercooler_list_threads
    
  2. Execute:

    mcp__watercooler__watercooler_list_threads()
    
  3. Present results:

    • Group by status (OPEN first, then CLOSED)
    • Show: topic, title, last activity, ball holder
    • Highlight actionable threads (where Claude has the ball)

Mode 2: Show Specific Thread (topic provided)

  1. Load tool:

    ToolSearch: select:mcp__watercooler__watercooler_read_thread
    
  2. Execute (use summary_only=true to keep response under ~500 tokens):

    mcp__watercooler__watercooler_read_thread(topic="<topic>", summary_only=true)
    
  3. Present:

    • Thread metadata
    • Recent entries summary
    • Current ball holder
    • Offer to fetch full entries if the user needs more detail

Mode 3: Filter by Status

  1. Parse status from arguments (case-insensitive: open/OPEN, closed/CLOSED)
  2. List all threads using watercooler_list_threads (same as Mode 1)
  3. Filter results client-side by matching the thread status field
  4. Present filtered list using the same format as Mode 1

--raw Flag

When --raw is present (in any mode), show the full JSON response after the human-readable summary. This is consistent with the recall skill behavior.

Example Invocations

  • /threads - List all threads
  • /threads open - Show only open threads
  • /threads mcp-migration - Show specific thread details
  • /threads --raw - Full JSON output
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 · 76 lines · 28 tokens per session scan A 9e5d54c6556a

Subscribe to this mod's changes

threads is a skill published in the GitHub repository mostlyharmless-ai/watercooler (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 564 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 2026-08-30.