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 n24q02m/wet-mcp --skill comparegit clone --depth 1 https://github.com/n24q02m/wet-mcpWrote 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/n24q02m/wet-mcp/compare)<a href="https://agentmods.dev/skills/n24q02m/wet-mcp/compare"><img src="https://agentmods.dev/badge/skills/n24q02m/wet-mcp/compare/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/n24q02m/wet-mcp/compare"><img src="https://agentmods.dev/badge/skills/n24q02m/wet-mcp/compare.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00015 | $0.00815 |
| Opus 5 | $0.00008 | $0.00407 |
| Sonnet 5 | $0.00003 | $0.00163 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
compare 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compare
Structured comparison of 2+ alternatives. Enforces a comparison matrix with consistent criteria so every alternative is evaluated on the SAME data points.
Steps
-
Define the comparison frame:
- List all alternatives to compare (minimum 2)
- Identify the use case or decision context (WHY is this comparison needed?)
- Ask the user for must-have requirements vs nice-to-have criteria
-
Define evaluation criteria before searching (prevents cherry-picking):
- Choose 5-8 criteria relevant to the use case
- Common technical criteria: performance, developer experience, ecosystem/community, documentation quality, maintenance status, license, cost, learning curve
- Weight criteria: must-have vs important vs nice-to-have
- Every criterion MUST be evaluated for ALL alternatives (no gaps)
-
Research each alternative using
searchandextract:search(action="search", query="[alternative] [criterion] benchmark OR comparison")- For each alternative, gather the SAME data points
- Prefer quantitative data (benchmarks, stars, download counts, release frequency)
- Note data recency — a 2023 benchmark may not reflect 2026 reality
- Use
extracton official docs for feature verification
-
Build the comparison matrix:
| Criterion (weight) | Alternative A | Alternative B | Alternative C | |---------------------|---------------|---------------|---------------| | Performance (must) | [data+source] | [data+source] | [data+source] | | DX (important) | [data+source] | [data+source] | [data+source] |- Every cell must have a value — use "No data found" if genuinely unavailable
- Include source links for verifiable claims
- Use consistent units (same benchmark suite, same metric)
-
Produce decision recommendation:
- Best for [use case X]: [Alternative] — because [reason based on must-have criteria]
- Best for [use case Y]: [Alternative] — if the use case differs
- Tradeoffs: What you give up with each choice
- Avoid if: Dealbreaker scenarios for each alternative
- Confidence: High (extensive data) / Medium (partial data) / Low (limited data)
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 · 71 lines · 15 tokens per session scan A 62b4eaf9929d
compare is a skill published in the GitHub repository n24q02m/wet-mcp (17 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 815 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
knowledge-audit
Review and clean up stored memories — find duplicates, contradictions, stale entries, and consolidate.
temporal-query
Answer time-travel questions over stored memory — what was believed at a past point in time, when a belief changed, and what replaced it. Use when the user says "as of", "back in", "at the time", "history of", "timeline", "what did I think then", or asks why a current memory contradicts an older one.
memory-commit
Use when the user explicitly says "remember this", "save this", "ghi nho", "luu lai", "save for next time", or otherwise asks to persist the immediately preceding context. Captures with the appropriate contexttype (decision, preference, fact, skill, task, conversation) so future sessions can retrieve it accurately.
recall-context
Use at session start, before significant decisions, or when a new task references a known project to recall mnemo memories matching the current working directory, recently edited files, or topic keywords. Helps maintain continuity across sessions and avoid redoing past research.
session-handoff
End-of-session knowledge capture — decisions, preferences, corrections, conventions, open questions.
passport-bootstrap
Use when the user installs mnemo-mcp on a fresh machine and wants to restore prior memory state from S3 or Google Drive (Phase 2 passport sync). Triggers on phrases like "set up mnemo on this machine", "restore my memory passport", "import passport", "bootstrap mnemo", or when the user says they got a new laptop / VM…