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-write-sectiongit 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-write-section)<a href="https://agentmods.dev/skills/akougkas/wtf-p/wtfp-write-section"><img src="https://agentmods.dev/badge/skills/akougkas/wtf-p/wtfp-write-section.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 | $0.00061 | $0.00566 |
| Opus 5 | $0.00030 | $0.00283 |
| Sonnet 5 | $0.00012 | $0.00113 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
wtfp-write-section 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 8d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write a WTF-P Section
Produce traceable academic prose without losing the plan, evidence, or author voice.
Select the action
- Use
write-sectionto execute one writing or revision plan. - Use
execute-outlineto execute independent plans in dependency-ordered waves. - Use
quickfor a narrow, low-risk change that does not justify a full plan.
Read references/actions.md for the selected action before editing manuscript content.
Apply the writing contract
- Resolve exact input and output paths inside the project root. Reject a missing, ambiguous, or already completed plan unless re-execution is explicitly approved.
- Read the full plan plus
project://manifest,project://state,project://decisions,project://structure/outline, the section record, linked context and research, source/evidence records, and only the prior prose needed for continuity. - Honor the author's decisions and the plan's scope. Record deviations and pause for any deviation that changes the thesis, evidence, structure, or promised result.
- Support claims only with verified project evidence. Never fabricate citations, quotations, results, measurements, methods, or limitations.
- Preserve citation keys, technical notation, figure and table references, and declared terminology.
- Verify the result backward against the plan and assigned claims. Classify remaining gaps as fix now, accepted debt, revision work, or human review.
- Update the Markdown section summary, synchronize the manuscript URI in
project://manifest, and update the section record andproject://stateonly after the manuscript write succeeds and validation is recorded. - Report changed files, word-count delta, evidence gaps, verification state, and the next review action.
Bound execution
- Obtain approval at configured writing gates and before replacing existing output.
- Parallelize only plans that declare no dependency or overlapping output. Finish and validate each wave before starting the next.
- Keep one writer responsible for each output file within a wave; serialize shared-file updates.
- Return version-control work only as a non-executed handoff for a separate action that declares and gates the effect.
- Keep
quickchanges atomic, narrowly scoped, and independently checked. Escalate to a formal plan when the task changes structure, multiple claims, or multiple sections.
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.
- 8d ago First seen · 38 lines · 61 tokens per session scan A f0db6891e31a
wtfp-write-section is a skill published in the GitHub repository akougkas/wtf-p (19 stars, last pushed 9d ago), licensed MIT. It adds 61 tokens to every session and 566 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.