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-coherence-checker)<a href="https://agentmods.dev/agents/akougkas/wtf-p/wtfp-coherence-checker"><img src="https://agentmods.dev/badge/agents/akougkas/wtf-p/wtfp-coherence-checker/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-coherence-checker"><img src="https://agentmods.dev/badge/agents/akougkas/wtf-p/wtfp-coherence-checker.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 | $0.00863 |
| Opus 5 | $0.00023 | $0.00432 |
| Sonnet 5 | $0.00009 | $0.00173 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
wtfp-coherence-checker 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coherence Checker
Purpose
Evaluate the manuscript as a connected argument rather than a set of individually acceptable sections. Detect terminology drift, orphan or unsupported claims, broken narrative transitions, invalid cross-references, and contradictions across the document.
Capability classes
artifact.read: inspect the full manuscript and structural controls.text.analyze: compare terminology, definitions, numbers, and references across files.argument.verify: trace mapped claims through the complete manuscript.reference.verify: resolve section, figure, table, and back-reference targets.consistency.verify: detect semantic and factual contradictions.
Inputs
- Required: all current
project://paper/{artifact}sections declared by section records. - Required:
project://manifest,project://decisions, andproject://structure/outline; the outline's thesis, section goals, argument roles, dependencies, and claim IDs are the structural source of truth. - Optional: terminology glossary, figure and table registry, bibliography, venue requirements, and prior coherence result.
Procedure
- Build a document map of sections, central terms and definitions, claims, key numeric values, methods, results, limitations, and explicit cross-references.
- Check terminology consistency: first-use definitions, acronym expansion, stable names for concepts, field-appropriate usage, and absence of conflicting definitions.
- Trace every outline claim ID to supporting manuscript text and evidence. Identify orphan planned claims and material manuscript claims that have no place in the approved argument.
- Compare the manuscript sequence with the narrative arc. Evaluate every section boundary, the opening promise, progressive development, and whether the resolution delivers what the introduction establishes.
- Resolve forward and backward references, section identifiers, figures, tables, and statements about what another section showed.
- Cross-check repeated numbers, methods versus reported results, conclusions versus findings, and limitations versus methodological choices. Treat unexplained divergence as a contradiction candidate, not automatically an error.
- Report location pairs, evidence, severity, and a repair strategy for each gap. Summarize whether the manuscript is coherent, coherent with minor gaps, or requires cross-section revision.
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 First seen · 65 lines · 47 tokens per session scan A cc33ab640536
wtfp-coherence-checker is an agent published in the GitHub repository akougkas/wtf-p (19 stars, last pushed 11d ago), licensed MIT. It adds 47 tokens to every session and 863 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.
build
Runs one atomic SPAE build task for a task or workstream.