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-research-literaturegit 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-research-literature)<a href="https://agentmods.dev/skills/akougkas/wtf-p/wtfp-research-literature"><img src="https://agentmods.dev/badge/skills/akougkas/wtf-p/wtfp-research-literature/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-research-literature"><img src="https://agentmods.dev/badge/skills/akougkas/wtf-p/wtfp-research-literature.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 | $0.00069 | $0.00494 |
| Opus 5 | $0.00034 | $0.00247 |
| Sonnet 5 | $0.00014 | $0.00099 |
| Haiku 4.5 | $0.00007 | $0.00049 |
Grade A, and why
wtfp-research-literature 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 13d 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.
Research Literature for WTF-P
Create an auditable bridge from external scholarship to manuscript claims.
Select the action
- Use
research-gapto investigate the literature or domain knowledge needed by a section. - Use
analyze-bibto characterize a bibliography and map references to the manuscript. - Use
check-refsto reconcile in-text citations and bibliography records.
Read references/actions.md for the selected action before searching or writing.
Apply the evidence contract
- Resolve the project root and the exact section or bibliography in scope.
- Read
project://manifest,project://decisions,project://structure/outline, existing source/evidence records, the section record, and its linked context before researching. - Separate records found in project files from records obtained externally. Record provenance for every external source.
- Prefer primary publications and authoritative scholarly indexes. Use secondary summaries only for discovery or context.
- Verify title, authors, year, venue, persistent identifier, and claim relevance before recommending a citation.
- Never invent a reference, metadata field, quotation, finding, page number, or citation key. Label unverified candidates explicitly.
- Require approval before using a paid or external service when project safety settings demand it, and before editing or removing bibliography entries.
- Report search scope, evidence limits, conflicting findings, unresolved metadata, and the next writing action.
Preserve research artifacts
- Store persistent section synthesis at
project://sections/{section}/researchand link it from the section record. - Store bibliographic identity and provenance in
project://sources/{source}and claim-level interpretation inproject://evidence/{evidence}. - Keep bibliography keys stable unless the author approves a migration and all references are updated together.
- Back up a bibliography before applying approved repairs.
- Do not claim a literature search is exhaustive unless the method, databases, dates, and stopping rule support that claim.
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.
- 13d ago First seen · 38 lines · 69 tokens per session scan A a2babd6577ae
wtfp-research-literature is a skill published in the GitHub repository akougkas/wtf-p (19 stars, last pushed 13d ago), licensed MIT. It adds 69 tokens to every session and 494 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
nutrition
Review or plan fueling and hydration for training and racing.
why
Explain the evidence and uncertainty behind a training decision.
easyreading-academic-paper
A Chinese-language guide for turning computer-vision and computer-graphics research papers into complete, easier-to-read academic HTML articles. It explains the original paper's sections, formulas, figures, tables, algorithms, experiments, limitations, and appendices.
worktrees
Manage Git worktrees as OMO safe isolated coding lanes for complex, risky, or parallel work.
cuopt-numerical-optimization-formulation
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.