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.
git 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/plugins/akougkas/wtf-p/gemini)<a href="https://agentmods.dev/plugins/akougkas/wtf-p/gemini"><img src="https://agentmods.dev/badge/plugins/akougkas/wtf-p/gemini/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/plugins/akougkas/wtf-p/gemini"><img src="https://agentmods.dev/badge/plugins/akougkas/wtf-p/gemini.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
wtfp 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.
What it actually says
{
"name": "wtfp",
"version": "0.8.0",
"description": "Portable academic research and writing workflows for Gemini CLI.",
"contextFileName": "GEMINI.md"
}
What ships with it
60 files beside gemini-extension.json 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.
- .wtfp-generated.json 29 KB
- actions/add-todo.json 1.2 KB
- actions/analyze-bib.json 2.5 KB
- actions/audit-milestone.json 1.7 KB
- actions/check-refs.json 2.1 KB
- actions/check-todos.json 1.1 KB
- actions/checkpoint.json 1.9 KB
- actions/contribute.json 1.4 KB
- actions/create-outline.json 2.2 KB
- actions/create-poster.json 1.3 KB
- actions/create-slides.json 1.4 KB
- actions/discuss-section.json 1.9 KB
- actions/execute-outline.json 3.3 KB
- actions/export-latex.json 1.7 KB
- actions/help.json 654 B
- actions/insert-section.json 1.5 KB
- actions/list-assumptions.json 891 B
- actions/map-project.json 1.7 KB
- actions/new-paper.json 1.7 KB
- actions/pause-writing.json 2.1 KB
- actions/plan-milestone-gaps.json 1.4 KB
- actions/plan-revision.json 1.6 KB
- actions/plan-section.json 3.3 KB
- actions/polish-prose.json 1.6 KB
- actions/progress.json 1.7 KB
- actions/quick.json 1.6 KB
- actions/remove-section.json 1.5 KB
- actions/report-bug.json 1.0 KB
- actions/request-feature.json 1.1 KB
- actions/research-gap.json 2.7 KB
- actions/resume-writing.json 2.2 KB
- actions/review-section.json 2.4 KB
- actions/settings.json 971 B
- actions/submit-milestone.json 2.1 KB
- actions/update.json 959 B
- actions/verify-work.json 1.6 KB
- actions/write-section.json 3.3 KB
- agents/wtfp-argument-verifier.md 6.5 KB
- agents/wtfp-citation-expert.md 6.9 KB
- agents/wtfp-citation-formatter.md 7.0 KB
- agents/wtfp-coherence-checker.md 6.5 KB
- agents/wtfp-outliner.md 7.2 KB
- agents/wtfp-plan-checker.md 6.3 KB
- agents/wtfp-prose-polisher.md 6.5 KB
- agents/wtfp-research-synthesizer.md 7.9 KB
- agents/wtfp-section-planner.md 7.0 KB
- agents/wtfp-section-reviewer.md 6.7 KB
- agents/wtfp-section-writer.md 7.4 KB
- aliases.lock.json 2.3 KB
- catalog.json 4.5 KB
- commands/wtfp/add-todo.toml 36 KB
- commands/wtfp/analyze-bib.toml 571 B
- commands/wtfp/audit-milestone.toml 590 B
- commands/wtfp/check-refs.toml 622 B
- commands/wtfp/check-todos.toml 30 KB
- commands/wtfp/checkpoint.toml 63 KB
- commands/wtfp/contribute.toml 642 B
- commands/wtfp/create-outline.toml 69 KB
- commands/wtfp/create-poster.toml 42 KB
- commands/wtfp/create-slides.toml 37 KB
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 Changed 90394dff1a58
- 23d ago Changed 35f1733ded31
- 29d ago Changed 40d40a52e8f0
- 1mo ago First seen · 7 lines scan A c90755abe6eb
wtfp is a plugin published in the GitHub repository akougkas/wtf-p (20 stars, last pushed 10d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-15.
Other plugins, from other repositories
ainb-fleet
LLM-facing skill teaching agents how to spawn ainb sessions correctly and how to use ainb fleet ... orchestration subcommands. Spawning covers the ainb run contract (always into a git worktree, plus the --parent shapes that silently misfire). Fleet covers multi-session broadcast, ack-gated sequence, blocked-sessi.
illustration
Explanatory & brand illustration skill starring Popa — a pink blob with a green sprout and a notepad — drawn as intricate hand-drawn sketchnotes. Workflow: digest → shot list → per-image generation → QA → deliver, with likeness-locked references. Invoke illustration or illustration:popa.
oh-my-antigravity
Legacy migration marker. Install the native oh-my-antigravity plugin with agy plugin install.
flow
Opinionated multi-step development workflow: kickoff → research → plan → develop → deploy → code-review-brief → review-triage → cleanup. Lightweight visual plans, fast iteration, atomic commits, TDD-first.
batonq-skills
Multi-CLI role skills for batonq autonomous coding agents — worker, judge, pr-runner, explorer, reviewer.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.