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.
npx skills add larsboes/Axon --skill academic-writinggit clone --depth 1 https://github.com/larsboes/AxonWrote 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/skills/larsboes/axon/academic-writing)<a href="https://agentmods.dev/skills/larsboes/axon/academic-writing"><img src="https://agentmods.dev/badge/skills/larsboes/axon/academic-writing/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/skills/larsboes/axon/academic-writing"><img src="https://agentmods.dev/badge/skills/larsboes/axon/academic-writing.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 | $0.00154 | $0.03472 |
| Opus 5 | $0.00077 | $0.01736 |
| Sonnet 5 | $0.00031 | $0.00694 |
| Haiku 4.5 | $0.00015 | $0.00347 |
Grade A, and why
academic-writing 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Academic Writing
Adds academic-writing-specific judgment a general-purpose model doesn't have by default: which genre a document belongs to and what that implies structurally, a checkable flow diagnostic, a genuinely adversarial critique pass (most academic-writing tooling is structurally biased toward gentle "looks good with minor fixes" feedback), and working citation-resolution/validation tooling. Four workflows, one skill — they share triggers ("help with this paper/thesis") even though invocation phrasing differs per workflow.
Default posture: never ghostwrite. Every workflow below produces sourced skeletons, critique, and findings — not net-new prose — unless the calling context (a project's own CLAUDE.md/skill, or an explicit user instruction this session) grants an exception. This mirrors the discipline a rigorous thesis/paper process already requires: the author's own reasoning is the thing being examined, not the assistant's.
Genre profile — pick this first, every workflow depends on it
Before running any workflow, determine which genre profile the target document belongs to:
- Empirical-CS / conference paper (has a method, baselines, ablations) →
references/genre-empirical-cs.md - DSR / qualitative thesis (design contribution against a knowledge base, single-case study) →
references/genre-dsr-qualitative.md
These are not interchangeable — see Gotchas. If genuinely unclear which applies, ask rather than guess; picking wrong produces confidently wrong-shaped output.
Workflow: Draft
Copy this checklist and track progress:
- [ ] Step 1: confirm genre profile + read the relevant genre reference
- [ ] Step 2: get the author's bullet points or messy draft (never invent them)
- [ ] Step 3: produce a sourced skeleton or a critique-then-example, per the no-ghostwriting posture
Step 1 — Orient. Read the genre-profile file (above) for the section being drafted (Abstract,
Introduction, Method, Discussion, etc. — empirical-CS profile names these explicitly; DSR profile
gives the generic Discussion shape and defers to the author's own confirmed chapter outline when one
exists). Read references/house-style.md for prose-mechanics rules (B1–B8) to apply to any generated
skeleton language.
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/adversarial-redteam.md 4.1 KB
- references/ai-cadence-tells.md 4.0 KB
- references/citation-workflows.md 4.5 KB
- references/critic-briefs.md 4.8 KB
- references/flow-diagnostics.md 5.5 KB
- references/genre-dsr-qualitative.md 5.2 KB
- references/genre-empirical-cs.md 3.7 KB
- references/house-style.md 3.4 KB
- scripts/check-citations.js 5.3 KB runs code
- scripts/resolve-papers.js 7.7 KB runs code
- scripts/scan-ai-tells.js 5.4 KB runs code
- scripts/validate-bib.js 5.1 KB runs code
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 · 226 lines · 154 tokens per session scan A e962868b5de8
academic-writing is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed today), licensed MIT. It adds 154 tokens to every session and 3,472 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
motion-frames
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…
webgl-halftone-drift
A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
frame-light-leak-cinema
Film light leaks, grain, 16:9 letterbox, and large serif type for cinematic openings or chapter cards.
card-xiaohongshu
Xiaohongshu-style knowledge cards, arranged as a swipeable multi-card carousel.