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.
npx skills add mostlyharmless-ai/watercooler --skill find-relatedgit clone --depth 1 https://github.com/mostlyharmless-ai/watercoolerWrote 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.
[](https://agentmods.dev/skills/mostlyharmless-ai/watercooler/find-related)<a href="https://agentmods.dev/skills/mostlyharmless-ai/watercooler/find-related"><img src="https://agentmods.dev/badge/skills/mostlyharmless-ai/watercooler/find-related/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mostlyharmless-ai/watercooler/find-related"><img src="https://agentmods.dev/badge/skills/mostlyharmless-ai/watercooler/find-related.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00023 | $0.00382 |
| Opus 5 | $0.00012 | $0.00191 |
| Sonnet 5 | $0.00005 | $0.00076 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
find-related 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 9d 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.
What it actually says
Find Related Content
Find content related to: $ARGUMENTS
Steps
-
Determine argument type:
- Entry ID: ULID format (e.g.,
01HQXYZ123ABC456DEF789GHJ) — exactly 26 characters matching^[0-9A-HJKMNP-TV-Z]{26}$(Crockford base32) - Description: Any other text
- Entry ID: ULID format (e.g.,
-
For Entry ID — use seeded similarity search:
ToolSearch: select:mcp__watercooler__watercooler_searchThen call:
mcp__watercooler__watercooler_search(seed_entry_id="<ulid>") -
For Description — use semantic search:
ToolSearch: select:mcp__watercooler__watercooler_searchThen call:
mcp__watercooler__watercooler_search(query="<description>", mode="entries", semantic=true, code_path="<repo root>") -
Present results:
- Group by thread/topic
- Show similarity scores for transparency
- Include brief context for each match
-
Suggest deeper exploration:
- Related threads to explore
- Follow-up queries
Example Invocations
/find-related 01HQXYZ123ABC456DEF789GHI- Find entries similar to this one/find-related git sync conflict resolution- Find related discussions/find-related branch parity implementation- Discover connected context
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.
- 9d ago First seen · 53 lines · 23 tokens per session scan A 48b4c81e0c58
find-related is a skill published in the GitHub repository mostlyharmless-ai/watercooler (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 382 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.
Other skills, from other repositories
cupynumeric-migration-readiness
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment…
deepstream-sop
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…
hsb-ip-packetizer
Choose or explain HSB Sensor RX packetizer fields for HOLOLINKdef.svh. Do not use for full defs, validation, or runtime APB programming.
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
i4h-workflow-validate
Run the root-level workflow runtime policy or rule-based rollouts and verify simulator success. Use for evaluation, checkpoints, or local controllers; do not use for replay or dataset annotation.
mcore-run-on-slurm
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDADEVICEMAXCONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.