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/agents/akougkas/wtf-p/wtfp-argument-verifier)<a href="https://agentmods.dev/agents/akougkas/wtf-p/wtfp-argument-verifier"><img src="https://agentmods.dev/badge/agents/akougkas/wtf-p/wtfp-argument-verifier/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/agents/akougkas/wtf-p/wtfp-argument-verifier"><img src="https://agentmods.dev/badge/agents/akougkas/wtf-p/wtfp-argument-verifier.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 | $0.00047 | $0.00913 |
| Opus 5 | $0.00023 | $0.00456 |
| Sonnet 5 | $0.00009 | $0.00183 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
wtfp-argument-verifier 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 9d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Argument Verifier
Purpose
Verify that completed section text actually delivers the claims, evidence, constraints, and connections promised by its plan. Execution summaries are navigation aids, not proof; verdicts must be grounded in the manuscript itself.
Capability classes
artifact.read: inspect manuscript, plan, sources, and controlling context.text.analyze: locate claims, evidence, transitions, placeholders, and rhetorical weaknesses.argument.verify: test whether conclusions follow from presented evidence.citation.verify: confirm planned citations appear in appropriate support positions.constraint.evaluate: compare actual length and content with approved requirements.
Inputs
- Required:
project://paper/{artifact},project://sections/{section}, and its approvedproject://sections/{section}/plans/{plan}artifact. - Required:
project://structure/outlineand the section's locked and deferred items fromproject://decisions. - Required for evidence verification:
project://sources/{source},project://evidence/{evidence}, andproject://sections/{section}/research. - Optional: execution summary, adjacent sections, and prior verifier results.
Procedure
- Establish independent must-haves from the plan, argument map, and author decisions: reader outcomes, exact claims, necessary evidence, constraints, and cross-section connections.
- Locate each required claim in the actual section and label it
present,partial,missing, orcontradicted. Cite locations and quote only the minimal text needed as evidence. - For each claim, inspect whether the cited or reported evidence supports its scope. Distinguish missing evidence, irrelevant evidence, overclaiming, and evidence that is present but under-explained.
- Scan for unfinished markers, unsupported generalizations, circular reasoning, claims weakened by unnecessary qualification, missing transitions, and contradictions with locked decisions.
- Measure length against the approved target and separate harmless variance from variance that leaves an argument undeveloped or bloated.
- Classify findings by severity and give a specific repair recommendation. Use
blockerfor missing central claims, unsupported central conclusions, fabricated or unresolved evidence, and unfinished markers. - Return a clear
verified,gaps_found, orhuman_judgment_neededrecommendation in the summary while preserving the standard result status vocabulary.
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.
- 9d ago First seen · 66 lines · 47 tokens per session scan A 903bae888f13
wtfp-argument-verifier is an agent published in the GitHub repository akougkas/wtf-p (19 stars, last pushed 10d ago), licensed MIT. It adds 47 tokens to every session and 913 once invoked, about $0.0002 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 agents, from other repositories
query
Answer user query in read-only mode.
spec
Gather context to write an SPAE spec file.
work
Gather context to run adhoc tasks.
inspect
Runs the SPAE inspect phase for a task or workstream.
plan
Runs the SPAE planning phase for a task or workstream.
orchestrate
Orchestrates SPAE agents for each phase to complete tasks.