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 kimgoetzke/coding-agent-configs --skill wtfgit clone --depth 1 https://github.com/kimgoetzke/coding-agent-configsWrote 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/kimgoetzke/coding-agent-configs/wtf)<a href="https://agentmods.dev/skills/kimgoetzke/coding-agent-configs/wtf"><img src="https://agentmods.dev/badge/skills/kimgoetzke/coding-agent-configs/wtf/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/kimgoetzke/coding-agent-configs/wtf"><img src="https://agentmods.dev/badge/skills/kimgoetzke/coding-agent-configs/wtf.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 | $0.00083 | $0.01601 |
| Opus 5.5 | $0.00033 | $0.00640 |
| Sonnet 5.5 | $0.00017 | $0.00320 |
| Haiku 4.5 | $0.00008 | $0.00160 |
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 1mo 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WTF
The user has many workstreams. They have come back to this one cold and no longer know what it is about. Your last message (a question you need answered, or findings you presented) made no sense to them. Rebuild their context from the top and then let them steer into whatever is still unclear.
Treat the user as if they last looked at this repository, ticket or document years ago and forgot most of it. They are intelligent and know the product. They do not remember the code, the names or the history.
Step 0: Pick the subject
- No argument: the subject is your most recent substantive message. If that message was a question, the subject is the decision you are asking for. If it was a report, the subject is the finding.
- Argument given: the subject is that term, quoted message or topic. Still anchor it in the current workstream.
Do not ask the user what they want explained. That is what they are asking you.
Step 1: Overview
One message, hard limit of roughly one A4 page (about 45 lines or 400 words, visuals included). Four parts, in order:
- Recap paragraph. Two to four sentences. What you were tasked with, by whom or from where (ticket, PR, message), what the goal is and roughly where you are now. Example: "I was tasked to investigate ticket ITS-123, which reports that some users are logged out after a few minutes. I traced the token refresh flow and found the cause. I now need you to decide how to fix it."
- The point. Two to five sentences in plain language stating what you are trying to communicate. For a question: what the decision is, why it is yours to make, and what happens if it is not made. For findings: what is wrong, where, and what it means for the user.
- The aspects. Break the subject into three to six constituent parts. One line each, in the order a newcomer needs them. Each line names the aspect using the term the codebase or ticket uses, followed by a plain-language gloss. Present them as a visual where one fits: a tree, a flow with box-drawing characters, or a small table. Number them so the user can refer to them.
- The question. Ask which aspect they want more detail on (see Asking).
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.
- 1mo ago First seen · 92 lines · 83 tokens per session scan A 8b7299a0e8bc
wtf is a skill published in the GitHub repository kimgoetzke/coding-agent-configs (2 stars, last pushed 19d ago), licensed MIT. It adds 83 tokens to every session and 1,601 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-11.
Other skills, from other repositories
bearings
Generate a "pick up where I left off" status report across all active Pi sessions. Use when the user asks for bearings, a status report, morning brief, catch-up, "where did I leave off", or "what's in the works". Reads live session state, composes a scannable 4-section digest, and writes a dated report to…
setup-maintenance
Maintain and improve a Pi coding agent setup over time — prevent drift AND find new leverage. Use when auditing setup health, before adding a package/extension, before publishing, or when asked "is my setup healthy" / "audit my setup" / "how do I keep this sharp".
agent-user-tools
Agent skill for user-tools - invoke with $agent-user-tools.
skill-iterative-loop
Run tasks in a loop until goals are met — use for iterative refinement, polling, or convergence.
sys-configure
Configure Claude Octopus — redirects to /octo:setup interactive wizard.
cog-braindump-capture
Capture raw thoughts with automatic domain classification and vault routing.