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/commands/akougkas/wtf-p/wtfp-new-paper)<a href="https://agentmods.dev/commands/akougkas/wtf-p/wtfp-new-paper"><img src="https://agentmods.dev/badge/commands/akougkas/wtf-p/wtfp-new-paper/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/commands/akougkas/wtf-p/wtfp-new-paper"><img src="https://agentmods.dev/badge/commands/akougkas/wtf-p/wtfp-new-paper.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 | $0.00016 | $0.00762 |
| Opus 5 | $0.00008 | $0.00381 |
| Sonnet 5 | $0.00003 | $0.00152 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
wtfp:new-paper scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start a new paper
@${PLUGIN_ROOT}/project/README.md @${PLUGIN_ROOT}/skills/wtfp-start-project/SKILL.md @${PLUGIN_ROOT}/skills/wtfp-start-project/references/actions.md
Record contract
Read: project://manifest, project://materials/{artifact}, project://paper/{artifact}.
Produce: project://manifest (create), project://config (create), project://state (create), project://decisions (create), project://structure/outline (create).
Resolve every logical URI through the host adapter. Portable v1 JSON records are the source of truth: schema-validate before a write, preserve stable IDs, update revision and timestamps where required, and replace records atomically. Never pass a literal logical URI to a shell command or infer record state from a legacy Markdown control file.
Manuscript prose and supporting context, research, plan, review, summary, handoff, and deliverable artifacts retain their authored format (normally Markdown). Link them from the relevant v1 record; do not convert manuscript prose into project-state JSON.
Procedure
- Detect existing project://manifest first; stop and offer inspection or repair rather than reinitializing it.
- Interview for identity, argument, document type, audience, requirements, exclusions, format, gates, safety, and author decisions.
- Preview the five v1 JSON records, validate every record and the cross-record
invariants, then create them atomically. In particular,
outline.sections[*].word_targetmust sum exactly tooutline.target_words; revise the proposed allocation before writing if it does not. Do not run git init, stage, commit, branch, or merge.
Safety and completion
Do not initialize a repository or run branch, stage, commit, merge, push, or publish operations. Use only the action's declared tools and capabilities; never attempt a shell command as a substitute for direct project read, listing, or write capabilities. If requested, return a clearly labeled optional handoff for a separately authorized action.
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.
- 11d ago First seen · 70 lines · 16 tokens per session scan A 029ed3a8e90e
wtfp:new-paper is a command published in the GitHub repository akougkas/wtf-p (19 stars, last pushed 12d ago), licensed MIT. It adds 16 tokens to every session and 762 once invoked, about $0.0001 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 commands, from other repositories
retro
Reflect on the current research session and collect improvement suggestions.
setup_research_plan
Set up or start a research project.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.