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 akougkas/wtf-p --skill wtfp-start-projectgit clone --depth 1 https://github.com/akougkas/wtf-pWrote 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/akougkas/wtf-p/wtfp-start-project)<a href="https://agentmods.dev/skills/akougkas/wtf-p/wtfp-start-project"><img src="https://agentmods.dev/badge/skills/akougkas/wtf-p/wtfp-start-project/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/akougkas/wtf-p/wtfp-start-project"><img src="https://agentmods.dev/badge/skills/akougkas/wtf-p/wtfp-start-project.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 | $0.00063 | $0.00509 |
| Opus 5 | $0.00032 | $0.00254 |
| Sonnet 5 | $0.00013 | $0.00102 |
| Haiku 4.5 | $0.00006 | $0.00051 |
Grade A, and why
wtfp-start-project 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 10d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start a WTF-P Project
Build a durable research-writing workspace before drafting prose.
Select the action
- Use
new-paperto interview the author and initialize a new project. - Use
map-projectto inventory an existing or brownfield project. - Use
create-outlineto turn the project thesis into an executable document structure.
Read references/actions.md for the selected action before changing files.
Apply the project contract
- Locate the project root selected by the host. Treat that contained root as the write boundary and resolve portable resources only through the adapter.
- Inspect existing material before proposing creation or replacement. Never overwrite a project protocol file silently.
- Read and schema-validate
project://configwhen present. Honor its approval gates, workflow checks, safety settings, parallelism, and output format. - Preserve the distinction between evidence, author decisions, and agent inference. Mark unknowns instead of inventing project facts.
- Ask for approval before replacing established structure or performing another declared consequential effect. Project initialization never initializes or mutates version control.
- Write planning artifacts atomically when possible, then read them back and cross-check their internal references.
- Finish with created or changed paths, unresolved questions, and the next recommended academic action.
Maintain structural invariants
- Keep the core argument in
project://manifestconsistent with the thesis, section roles, and claim assignments inproject://structure/outline. - Give every outline and section-record entry a unique stable identifier, goal, word budget, status, and dependency wave.
- Require every initialized or approved outline's
sections[*].word_targetvalues to sum exactly to itstarget_words; revise the allocation before writing when they do not. - Use relative project paths only. Do not embed host installation paths, client commands, model names, or tool-specific syntax.
- Never treat a generated citation, claim, venue rule, or project statistic as verified without a source.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 39 lines · 63 tokens per session scan A 943cc21e2962
wtfp-start-project is a skill published in the GitHub repository akougkas/wtf-p (19 stars, last pushed 11d ago), licensed MIT. It adds 63 tokens to every session and 509 once invoked, about $0.0003 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
oh-my-opencode-slim
Configure and improve oh-my-opencode-slim for the current user. Use when users want to tune agents, models, prompts, custom agents, skills, MCPs, presets, or plugin behavior. Also use when recurring workflow friction suggests a safe config or prompt improvement.
clonedeps
Clone important project dependency source code into an ignored local workspace so OpenCode can inspect library internals. Use when the user asks to clone dependencies, inspect dependency/source internals, understand SDK/framework behavior from source, debug library implementation details, or make core dependency repos…
codemap
Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping.
deepwork
High-cost orchestrator workflow for large, high-risk, multi-phase coding efforts with meaningful dependencies and review gates. Do not activate for routine multi-file changes.
worktrees
Manage Git worktrees as OMO safe isolated coding lanes for complex, risky, or parallel work.
simplify
Simplifies code for clarity without changing behavior. Use for readability, maintainability, and complexity reduction after behavior is understood.