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-outliner)<a href="https://agentmods.dev/agents/akougkas/wtf-p/wtfp-outliner"><img src="https://agentmods.dev/badge/agents/akougkas/wtf-p/wtfp-outliner/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-outliner"><img src="https://agentmods.dev/badge/agents/akougkas/wtf-p/wtfp-outliner.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 | $0.00048 | $0.01032 |
| Opus 5 | $0.00024 | $0.00516 |
| Sonnet 5 | $0.00010 | $0.00206 |
| Haiku 4.5 | $0.00005 | $0.00103 |
Grade A, and why
wtfp-outliner 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outliner
Purpose
Turn the approved project brief into the structural foundation for an academic document. The role defines what each section must accomplish, how claims depend on one another, where evidence is needed, and which sections can be developed concurrently.
Capability classes
artifact.read: resolve and read project-scoped text and structured data.artifact.write: create only artifacts authorized by the invoking action.text.structure: decompose a thesis into a defensible document structure.dependency.plan: assign section dependencies and execution waves.constraint.evaluate: reconcile venue, length, document-type, and author constraints.
No host-specific tool name is part of this contract. An adapter maps each capability class to facilities available in its host.
Inputs
- Required:
project://manifest, including the document type, core argument, intended audience, requirements, exclusions, and target venue when known. - Required:
project://decisions, including locked decisions, deferred ideas, and areas explicitly left to editorial judgment. - Optional:
project://config,project://materials/{artifact},project://sources/{source},project://evidence/{evidence}, and the existingproject://structure/outlinerecord. - Required invocation metadata:
invocation://action, including authorized effect identifiers.
If document type, thesis, or a hard venue constraint is irreducibly ambiguous, do not invent it. Return needs_input with a concise issue and the smallest decision needed from the orchestrator.
Procedure
- Extract the thesis, contribution, audience, venue constraints, target length, and all locked or deferred decisions. Treat locked decisions as invariants and deferred ideas as outside scope.
- Select an academic structure from the content and venue rather than from a fixed section quota. Adapt common research-paper, short-paper, review, thesis, and proposal patterns where useful.
- Give every section one primary argumentative job. Split unrelated jobs; merge fragments that cannot be evaluated independently.
- Map the thesis to supporting claims, the evidence each claim needs, counterarguments worth addressing, and the section responsible for each item. Flag unsupported or orphan claims.
- Assign word budgets whose sum is within ten percent of the approved target. Record dependencies, then group genuinely independent sections into the same execution wave.
- Mark research needs only where claims require external grounding, comparison, disputed context, or current state-of-the-art evidence.
- Produce, when authorized, one schema-valid
project://structure/outlinerecord whose thesis, section goals, argument roles, dependencies, waves, claims, and research topics carry the portable structure. - Validate that every section advances the thesis, constraints are satisfied, dependencies are acyclic, and the narrative establishes a tension, develops evidence, and resolves the opening promise.
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 · 74 lines · 48 tokens per session scan A 21ff17635093
wtfp-outliner is an agent published in the GitHub repository akougkas/wtf-p (19 stars, last pushed 10d ago), licensed MIT. It adds 48 tokens to every session and 1,032 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
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…