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.
/plugin marketplace add akougkas/wtf-pnpx agentmods add plugins/akougkas/wtf-p/claudegit clone --depth 1 https://github.com/akougkas/wtf-pGrade 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 2d 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": "0.6.0-rc.2",
"description": "Portable academic research and writing workflows with stable wtfp actions.",
"author": {
"name": "akougkas",
"url": "https://github.com/akougkas"
},
"homepage": "https://github.com/akougkas/wtf-p",
"repository": "https://github.com/akougkas/wtf-p",
"license": "MIT"
}
What ships with it
1 file beside plugin.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.
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.
- 2d ago First seen · 13 lines scan A 00c6c9eb1d2e
wtfp is a plugin published in the GitHub repository akougkas/wtf-p (18 stars, last pushed 3d 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 2026-08-30.
Other plugins, from other repositories
ainb-hooks
Emit every safely observable Claude Code lifecycle event into Hangar's durable provider log. User-facing events still reach ainb-notifyd over its Unix socket. The same notify.sh powers ATC structured control when installed with AINBMANAGED=atc. stallguard.py additionally blocks turn-end when a session would idle on i.
caveman-stats
Caveman mode lifecycle hooks: PostToolUse updates .caveman-statusline-suffix with token savings estimate; PreCompact re-injects caveman ruleset so mode survives context compaction.
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.
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 naturally without changing what it says.