Borrowing it
Nothing to install: this file belongs to u9401066/med-paper-assistant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/u9401066/med-paper-assistant/master/.agents/skills/academic-writing-harness/SKILL.mdgit clone --depth 1 https://github.com/u9401066/med-paper-assistantWrote 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/u9401066/med-paper-assistant/academic-writing-harness)<a href="https://agentmods.dev/skills/u9401066/med-paper-assistant/academic-writing-harness"><img src="https://agentmods.dev/badge/skills/u9401066/med-paper-assistant/academic-writing-harness/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/u9401066/med-paper-assistant/academic-writing-harness"><img src="https://agentmods.dev/badge/skills/u9401066/med-paper-assistant/academic-writing-harness.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 | $0.00029 | $0.00856 |
| Opus 5 | $0.00015 | $0.00428 |
| Sonnet 5 | $0.00006 | $0.00171 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
academic-writing-harness 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 12d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Academic Writing Harness
Use this skill for end-to-end academic writing, revision, review, or export in
Codex and OpenClaw. Claude Code uses the matching skill under
.claude/skills/academic-writing-harness/.
Required reading
- Read
.copilot-mode.jsonandAGENTS.mdbefore repository operations. - Read
docs/harness/academic-writing-workflow.mdcompletely. It is the platform-neutral workflow and artifact contract. - Read
docs/harness/evaluation-contract.mdbefore running or changing a quality evaluation. It defines solver/scorer separation, evidence locators, budgets, frozen fixtures, and release evidence. - Read the relevant source skill for the requested phase:
.claude/skills/project-management/SKILL.mdfor setup and output type..claude/skills/literature-review/SKILL.mdfor evidence discovery..claude/skills/draft-writing/SKILL.mdfor section drafting..claude/skills/manuscript-review/SKILL.mdfor structured review..claude/skills/word-export/SKILL.mdfor DOCX delivery..claude/skills/auto-paper/SKILL.mdonly for full autopilot runs.
Operating contract
- Resume recorded workspace and project state before starting a new phase.
- Select an output profile before planning. Do not force every academic output into IMRaD.
- Build a claim-evidence ledger before prose and keep source identifiers near every material claim. Evidence locators must include a stable source revision, section/page/paragraph/span, offsets when available, and a hash of the cited span; a model summary is not a locator.
- Register exemplars separately from evidence sources. Extract only declared structural or stylistic features and record provenance.
- Write section-by-section, then score the persisted artifact in a separate, read-only pass. A solver must not award its own gate result or alter scorer fixtures, thresholds, or expected outcomes.
- Declare per-stage tool/model/time/retry budgets and enforce source-dominance limits. Exceeding a budget or letting one source dominate is a recorded gate outcome, not a reason to hide or truncate audit evidence.
- Run deterministic hooks and satisfy each hard gate before advancing. Release claims require frozen positive, negative, mutation, degraded, and resume fixtures plus the command, environment, counts, hashes, and failure details.
- Treat human acceptance as an external authority boundary. An Agent/MCP may
inspect or revoke a host-issued Ed25519 confirmation receipt, but must never
mint one by labeling its own input as
human; receipts bind the project, reviewed artifact/state hashes, named reviewer, confirmation identifier, and time, and are verified only against host-configured public keys. - Before inserting an image, re-run the read-only C2PA and pinned visible/open-DWT checks against its current bytes. Preserve the original, require documented review for raster uncertainty, and never equate a negative detector result with proof that no watermark exists.
- Keep verified source data, agent interpretation, and user-authored notes in separate trust layers.
- Finish with cross-section review, reference verification, export validation, audit artifacts, and Memory updates.
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.
- 12d ago First seen · 73 lines · 29 tokens per session scan A a262d300493d
academic-writing-harness is a skill published in the GitHub repository u9401066/med-paper-assistant (12 stars, last pushed 10d ago), licensed Apache-2.0. It adds 29 tokens to every session and 856 once invoked, about $0.0001 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 skills, from other repositories
citation-manager
Format and manage citations — APA, MLA, Chicago, IEEE, and Vancouver styles with BibTeX export.
manuscript-reframe
Reframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.
peer-review
Review another author's manuscript, paper, thesis chapter, proposal, or preprint as an external reviewer. Use when asked to evaluate novelty, significance, gap-contribution fit, claim-evidence adequacy, methods, evaluation, overclaim risks, structure, writing, required revisions, or recommendation without rewriting…
revision-escalation
A revision-control guide for writing, coding, manuscripts, rebuttals, and restructuring work. It says to stop applying local edits after the same problem remains unresolved through three attempts and check the underlying requirements or structure.
extremerouter-web-search
Web search via ExtremeRouter /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity. Use when the user wants to search the web, look up information, find articles, or query a search engine.
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.