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-review-manuscriptgit 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-review-manuscript)<a href="https://agentmods.dev/skills/akougkas/wtf-p/wtfp-review-manuscript"><img src="https://agentmods.dev/badge/skills/akougkas/wtf-p/wtfp-review-manuscript/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-review-manuscript"><img src="https://agentmods.dev/badge/skills/akougkas/wtf-p/wtfp-review-manuscript.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 | $0.00080 | $0.00577 |
| Opus 5 | $0.00040 | $0.00289 |
| Sonnet 5 | $0.00016 | $0.00115 |
| Haiku 4.5 | $0.00008 | $0.00058 |
Grade A, and why
wtfp-review-manuscript 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 12d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review a WTF-P Manuscript
Turn critique into traceable evidence, decisions, and executable revisions.
Select the action
- Use
review-sectionfor citation, logic, and requirements review under a chosen reviewer stance. - Use
verify-workfor resumable, one-criterion-at-a-time author acceptance. - Use
polish-prosefor meaning-preserving voice and clarity edits. - Use
audit-milestonefor whole-manuscript readiness checks. - Use
plan-milestone-gapsto convert audit findings into section-scoped fix plans.
Read references/actions.md for the selected action before reviewing or editing.
Apply the review contract
- Resolve the exact
project://paper/{artifact}, section record, and authored planning artifacts in scope. - Read requirements from
project://manifest, claim structure fromproject://structure/outline, the relevant plan,project://decisions, source/evidence records, and manuscript text. - Distinguish mechanical checks, logical judgment, rubric compliance, and author preference. Do not collapse them into one score.
- Cite file locations or passages for every actionable finding. State the failed criterion, evidence, severity, and a bounded recommendation.
- Never treat a stylistic preference as a factual error or silently change meaning while polishing.
- Preserve acceptance-test progress in a
project://validations/{validation}record after each response so verification can resume without replay. - Re-run the check affected by a fix and screen for regressions elsewhere.
- Report passes, gaps, skipped checks, limitations, created artifacts, and the next remediation or delivery action.
Preserve review integrity
- Do not invent citation validation, evidence coverage, review completion, or compilation success.
- Use the validation schema's
passed,warning,failed, andnot-applicablecheck statuses distinctly; every non-applicable check needs a reason. - Keep reviewer findings separate from author acceptance results.
- Require approval before applying prose edits or changing the issue scope.
- Group milestone gaps by section and compatible output path; route review-only gaps to review instead of generating fake writing tasks.
- A milestone is
passedonly when every required check passes; optionalnot-applicablechecks remain visible.
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.
- 12d ago First seen · 41 lines · 80 tokens per session scan A 24fe6f2ca0f8
wtfp-review-manuscript is a skill published in the GitHub repository akougkas/wtf-p (19 stars, last pushed 13d ago), licensed MIT. It adds 80 tokens to every session and 577 once invoked, about $0.0004 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.