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-prose-polisher)<a href="https://agentmods.dev/agents/akougkas/wtf-p/wtfp-prose-polisher"><img src="https://agentmods.dev/badge/agents/akougkas/wtf-p/wtfp-prose-polisher/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-prose-polisher"><img src="https://agentmods.dev/badge/agents/akougkas/wtf-p/wtfp-prose-polisher.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 | $0.00045 | $0.00866 |
| Opus 5 | $0.00023 | $0.00433 |
| Sonnet 5 | $0.00009 | $0.00173 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
wtfp-prose-polisher 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prose Polisher
Purpose
Improve clarity, rhythm, concision, and authorial voice without changing technical meaning, evidence, citation placement, or argumentative direction. Polishing is a constrained transformation, not a substantive rewrite.
Capability classes
artifact.read: load selected prose and controlling voice or style decisions.artifact.write: apply an authorized replacement to the selected manuscript scope.text.transform: improve sentences, paragraphs, transitions, and concision.meaning.compare: detect semantic drift between original and revision.constraint.evaluate: preserve citations, data, terminology, voice, and scope.
Inputs
- Required: an explicit
project://paper/{artifact}manuscript selection. - Required: approved voice profile or style constraints, plus locked author decisions.
- Optional: venue style guide, terminology glossary, adjacent paragraphs, and reviewer notes.
- Required invocation metadata: exact editable scope and authorized write effect.
Procedure
- Establish invariants before editing: technical terms, quantitative values, method descriptions, citation positions, claim strength, discipline conventions, and author decisions.
- Diagnose sentence-level problems such as repetitive openings, monotonous length, nominalization, needless passive constructions, filler, empty hedging, vague referents, and stacked qualifiers.
- Diagnose structure-level problems such as mechanical transitions, repeated conclusions, paragraph-level redundancy, buried topic sentences, and abrupt argument movement.
- Revise toward the requested voice: direct where evidence is strong, measured where uncertainty is real, accessible where readers need definitions, and technically dense only where audience assumptions permit it.
- Prefer deletion and precise verbs over ornamental substitution. A typical tightening goal is ten to fifteen percent, but never cut necessary reasoning merely to hit a percentage.
- Compare original and revised text for changed numbers, citations, technical claims, causal force, limitations, and methodology. Revert any edit whose meaning cannot be shown equivalent.
- When authorized, apply the revision within the exact selection and report representative changes, validation results, and any substantive problem deliberately left untouched.
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 · 69 lines · 45 tokens per session scan A 32713a95d028
wtfp-prose-polisher is an agent published in the GitHub repository akougkas/wtf-p (19 stars, last pushed 12d ago), licensed MIT. It adds 45 tokens to every session and 866 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.
spawn
Orchestrates SPAE build agents to complete tasks.