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 agentmods add skills/wave-engineering/mcp-server-wtf/wtfnpx skills add Wave-Engineering/mcp-server-wtf --skill wtfgit clone --depth 1 https://github.com/Wave-Engineering/mcp-server-wtfWrote 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/wave-engineering/mcp-server-wtf/wtf)<a href="https://agentmods.dev/skills/wave-engineering/mcp-server-wtf/wtf"><img src="https://agentmods.dev/badge/skills/wave-engineering/mcp-server-wtf/wtf.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00524 |
| Opus 5 | $0.00000 | $0.00262 |
| Sonnet 5 | $0.00000 | $0.00105 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
wtf 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/wtf — Start a Troubleshooting Session
Launch the WTF flight recorder for a new troubleshooting incident. Archives any prior incident, prompts for an optional title, then puts Claude into flight recorder mode where significant observations, theories, and corrective actions are journaled automatically.
Resolve Intent
Parse the invocation arguments:
- No arguments — start a new troubleshooting session (default behavior).
record <text>— shorthand for/wtf now <text>. Route directly to the/wtf nowskill with the provided text, then stop.
Steps
1. Archive prior incident
Call the wtf_freshell MCP tool with no arguments. This archives any
currently active incident and creates a fresh one.
2. Prompt for incident title
Ask the user:
What are you troubleshooting? (optional — press Enter to skip)
If the user provides a title, call wtf_freshell again with { "title": "<user's title>" } to set the title on the newly created incident.
Wait for the user's response before proceeding.
3. Confirm and activate flight recorder mode
Tell the user the session is active, then follow these behavioral instructions for the remainder of the conversation:
You are now in WTF flight recorder mode. A background journal is capturing every tool call automatically. In addition to that automatic capture, you should:
- Call
wtf_nowwithgen_type: "crafted"andaction_type: "breadcrumb"when you observe something diagnostically significant - Call
wtf_nowwithgen_type: "crafted"andaction_type: "theory"when you form a hypothesis about the root cause - Call
wtf_nowwithgen_type: "crafted"andaction_type: "action"when you take a corrective action (not exploratory commands)
Bias toward recording. When in doubt, record it. A noisy journal can be distilled; a silent journal cannot be recovered.
At any time, the user may call wtf_happened to see the current timeline,
or /wtf now to add their own observations.
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.
- 5d ago First seen · 64 lines · 0 tokens per session scan A bca5220298c5
wtf is a skill published in the GitHub repository Wave-Engineering/mcp-server-wtf (0 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 524 tokens. 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 2026-08-31.
Other skills, from other repositories
verify-task
Verify a work item is actually done by running the V- validation rows its issue cites. Maps V- IDs to the CI step / test command via VALIDATION.md, runs them, reports pass/fail per row.
promote-idea
Promote an Inbox bullet from BACKLOG.md to either a GitHub issue (work commitment) or a briefing (briefings/B-NNNN-.md, research/decision support). Asks which based on whether the work is committed or still needs thinking. Removes the original bullet.
search
Hybrid search across Captain Memo's local memory + skills + observations. Use when the user types /captain-memo:search to retrieve top hits without the model having to decide whether to call searchall on its own.
observations
List recent captured session observations (the Haiku-summarized voyage logs). Use when the user wants to see what Captain Memo has logged from past sessions.
doctor
Health probe across Captain Memo's components — embedder service, worker service, config, plugin registration, plugin manifest. Use when the user types /captain-memo:doctor or when something seems wrong.
bun-runtime-http
Covers Bun.serve, HTTP server configuration, routing, streaming responses, WebSockets, TLS/SSL, and middleware with Bun's native APIs.