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 | $0.03582 |
| Opus 5.5 | $0.00062 | $0.01433 |
| Sonnet 5.5 | $0.00031 | $0.00716 |
| Haiku 4.5 | $0.00015 | $0.00358 |
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 1mo 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 — 231 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 5.6 KB
- references/citation-workflows.md 4.5 KB
- references/critic-briefs.md 4.8 KB
- references/flow-diagnostics.md 5.6 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 5.9 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.
- 1mo ago Changed · +5 lines 64d570957017
- 2mo 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 1mo ago), licensed MIT. It adds 154 tokens to every session and 3,582 once invoked, about $0.0006 per session on Opus 5.5. 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.
academic-writing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| academic-writinglarsboes/Axon | Skill | 1 | 1mo ago | MIT | A | 154 | Claude Code |
| ligandmpnnaipoch/open-science | Skill | 5.5k | today | Apache-2.0 | A | 100 | Claude Code, Codex |
| evo2aipoch/open-science | Skill | 5.5k | today | Apache-2.0 | A | 83 | Claude Code, Codex |
| create-agentPM-Shawn/Abu-Cowork | Skill | 419 | 3d ago | Apache-2.0 | A | 13 | Claude Code |
| content-monitorCoWork-OS/CoWork-OS | Skill | 537 | today | MIT | A | 16 | Claude Code, Codex |
| llm-wikiCoWork-OS/CoWork-OS | Skill | 537 | today | MIT | A | 27 | Claude Code, Codex |
| simplifyCoWork-OS/CoWork-OS | Skill | 537 | today | MIT | A | 24 | Claude Code, Codex |