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 winstonkoh87/Athena-Public --skill academic-deliverygit clone --depth 1 https://github.com/winstonkoh87/Athena-PublicWrote 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/winstonkoh87/athena-public/academic-delivery)<a href="https://agentmods.dev/skills/winstonkoh87/athena-public/academic-delivery"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/academic-delivery/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/winstonkoh87/athena-public/academic-delivery"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/academic-delivery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.01214 |
| Opus 5 | $0.00018 | $0.00607 |
| Sonnet 5 | $0.00007 | $0.00243 |
| Haiku 4.5 | $0.00004 | $0.00121 |
Grade A, and why
academic-delivery 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Academic Delivery Skill
Purpose: Structured pipeline for academic/knowledge deliverables. Prevents the V1-is-weak failure mode by auto-triggering adversarial review. Origin: Extracted from real-world execution of client assignments. Every assignment manually reconstructed this pipeline — now it's codified.
The 8-Step Pipeline
Step 1: INTAKE
- Parse brief/requirements document
- Extract: word count, format (essay/report/problem set), rubric criteria, deadline, client name
- Identify prescribed frameworks or sources (e.g., "use Hirshfield as critical lens")
- Log to
.context/client_work/pricing_log.mdif commercial
Step 2: SCOPE
- Classify deliverable type:
- Essay (argumentative, comparative, reflective)
- Report (technical, research, capstone)
- Problem Set (calculations, code, SPSS)
- Presentation (slides, pitch deck)
- Estimate complexity (Λ score)
- If commercial: trigger
client-pricingskill for quote generation
Step 3: RESEARCH
- Load domain context via Exocortex (
smart_search.py) - If external research needed: trigger
deep-research-loop(Cluster #12) - Extract key frameworks, models, citations
- Build a reference spine (3–7 sources minimum for essays)
Step 4: DRAFT (V1)
- Write full first draft to spec
- Embed citations inline
- Target 90–95% of word count (leave room for red-team additions)
- DO NOT deliver V1. V1 is always a working draft, never the output.
Step 5: RED-TEAM (Mandatory — Auto-Triggered)
[!IMPORTANT] This step is non-negotiable. It fires automatically after Step 4. Shipping V1 with zero counter-readings and zero formal analysis is the canonical failure mode.
- Feed V1 through adversarial review (Cluster #8 —
red-team-review) - Evaluate against:
- Counter-reading: Does the draft contain at least one steelmanned opposing interpretation + rebuttal? (~80 words, non-negotiable)
- Formal analysis: For literary/theoretical work — does it engage with the form (enjambment, structure, methodology), not just content?
- Evidence density: Every claim backed by textual evidence or citation?
- Rubric alignment: Does the draft hit every criterion in the brief?
- Genre compliance: Is the output in the correct academic register? (MLA vs APA vs report format)
- Generate a fix list with accept/reject decisions for each criticism
- Reject invalid criticisms (category errors, phantom rubric scoring, n=1 methodology applied to literary analysis)
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 · 112 lines · 36 tokens per session scan A 2358f179da9e
academic-delivery is a skill published in the GitHub repository winstonkoh87/Athena-Public (587 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 1,214 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 skills, from other repositories
imap-smtp-email
Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.
task_automation
Design effective automated workflows using scheduled tasks, prompt chaining, and delivery channels.
skill-factory
A workflow that examines completed session work and turns reusable patterns into Claude Code skills.
session-wrap
Use when wrapping up a session before ending. 4 parallel subagents detect doc updates, repeated patterns, learning points, and follow-ups, then a verifier deduplicates and presents choices. Triggers on /session-wrap, session wrap, session cleanup, end of session.
lark-cli
Use when the user wants to operate Lark or Feishu via the local lark-cli (@larksuite/cli), including install, app credentials, OAuth, readiness checks, and safe read/write boundaries.
opencli
Use when the user wants to use websites, browser login sessions, Electron apps, or external CLIs through a local OpenCLI setup, especially when setup guidance, readiness checks, and safe task execution are needed.