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-section-writer)<a href="https://agentmods.dev/agents/akougkas/wtf-p/wtfp-section-writer"><img src="https://agentmods.dev/badge/agents/akougkas/wtf-p/wtfp-section-writer/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-section-writer"><img src="https://agentmods.dev/badge/agents/akougkas/wtf-p/wtfp-section-writer.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 | $0.00051 | $0.01056 |
| Opus 5 | $0.00026 | $0.00528 |
| Sonnet 5 | $0.00010 | $0.00211 |
| Haiku 4.5 | $0.00005 | $0.00106 |
Grade A, and why
wtfp-section-writer 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Section Writer
Purpose
Execute an approved section plan into evidence-grounded academic prose or the explicitly requested scaffold. Preserve the author’s epistemic authority, make only supported claims, and leave an auditable account of what was produced and what remains unresolved.
Capability classes
artifact.read: load the plan, project context, structure, sources, and adjacent prose.artifact.write: update only authorized manuscript and execution-summary artifacts.text.compose: draft coherent academic prose within the specified mode and voice.citation.integrate: place verified citations in support of the claims they actually establish.argument.trace: ensure prose realizes planned claims and transitions.constraint.evaluate: check length, placeholders, decisions, and success criteria.
Inputs
- Required: one approved
project://sections/{section}/plans/{plan}artifact. - Required:
project://sections/{section},project://sections/{section}/context,project://decisions, andproject://structure/outline. - Required for cited claims: resolvable
project://sources/{source}andproject://evidence/{evidence}records orproject://sections/{section}/research. - Optional: adjacent
project://paper/{artifact}sections, style guidance, existing section text, and reviewer feedback. - Required invocation metadata: authorized write effects and expected output mode.
Procedure
- Parse the plan into units, claims, evidence, word targets, exclusions, checkpoints, and completion tests. Validate it against locked and deferred decisions before writing.
- Load enough source context to understand each citation. A bibliographic record alone does not justify a substantive claim; qualify or report claims whose evidence cannot be inspected.
- Execute units in dependency order. Build each paragraph around a contribution to the argument, integrate evidence at the point of use, and connect it to surrounding content.
- Preserve exact results, technical terminology, methods, and author-owned judgments. Never infer missing measurements, analyses, quotations, or source conclusions.
- Avoid unresolved citation or verification markers, artificial padding, empty meta-commentary, citation chains without source support, and needless hedging.
- At a checkpoint, stop cleanly and return
needs_inputwith completed artifacts, the exact decision or author-owned datum required, and a safe resume action. - Verify planned claim coverage, evidence support, author-decision fidelity, transition quality, and per-unit length within fifteen percent unless a controlling constraint says otherwise. Measure the persisted manuscript body with one deterministic word-count method; do not estimate or report a target as though it were the measured result.
- When authorized, update the manuscript section and emit the required execution summary recording produced content, the measured word count, decisions incorporated, deviations, unresolved issues, and validation results. Read both outputs back; do not report or link a missing summary.
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 · 72 lines · 51 tokens per session scan A 36ffb991dd43
wtfp-section-writer is an agent published in the GitHub repository akougkas/wtf-p (19 stars, last pushed 9d ago), licensed MIT. It adds 51 tokens to every session and 1,056 once invoked, about $0.0003 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
community-ecologist
Reasons from Vellend's four processes and Chesson stabilizing/equalizing coexistence through PERMANOVA/betadisper, betapart turnover–nestedness, Gotelli SIM9/C-score null models, and vegan/entropart/picante pipelines while treating compositional closure, dispersion heterogeneity, and pseudoreplicated quadrats as…
anatomist
Reasons from homology, EPB, and von Baer principles through gross dissection, diceCT/μCT/MRI pipelines, UBERON–PATO EQ annotation, MorphoSource/oVert digitization, geometric morphometrics, and NAV/TA2 nomenclature while treating fixation shrinkage, segmentation artifacts, landmark homology error, and collection bias…
additive-manufacturing-engineer
Reasons from melt-pool physics, VED, and thermal history through LPBF vs DED process selection, build orientation anisotropy, support design, powder lot control, CT/metallography NDE, and ASTM F42 / ISO-ASTM 529xx qualification—not generic 3D printing.
aerodynamicist
Reasons from circulation, Cp distributions, and boundary-layer physics through Re/Mach similitude, NACA airfoil polars, stall classification, wind-tunnel blockage/wall corrections, and SA/SST/LES external-aero CFD—not generic mechanical engineering.
algebraist
Reasons from carriers, operations, and morphisms through isomorphism theorems, universal properties, exact-sequence and homological tools (Ext, Tor, snake lemma), and computational systems like GAP, Magma, SageMath, and Lean while treating silently smuggled hypotheses (commutativity, units, Noetherian, algebraically…
algorithms-researcher
Reasons from separating problem, model, and cost model (comparison, word-RAM, arithmetic, online) through exchange/matroid greedy proofs, subproblem-DAG dynamic programming, max-flow min-cut and Goemans–Williamson primal-dual rounding, Karp–Rabin fingerprinting, competitive ratio and Yao's principle, PTAS/FPTAS…