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 agentmods add skills/shoberman2/schoolbridge/skillnpx skills add Shoberman2/schoolbridge --skill skillgit clone --depth 1 https://github.com/Shoberman2/schoolbridgeWhat 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 | $0.00066 | $0.01180 |
| Opus 5 | $0.00033 | $0.00590 |
| Sonnet 5 | $0.00013 | $0.00236 |
| Haiku 4.5 | $0.00007 | $0.00118 |
Grade A, and why
schoolbridge 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 yesterday.
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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
schoolbridge — assignments, grades & announcements
schoolbridge is a read-only CLI bridge to the student's school LMS (Canvas first; provider-pluggable). It never submits, messages, or changes anything at school — it only reads.
Setup (once)
Run schoolbridge courses. If it errors with "Canvas is not configured":
- Ask the user for their school's Canvas URL and an access token (created in Canvas → Account → Settings → Approved Integrations → "+ New Access Token").
- Run:
schoolbridge init --base-url <url> --token <token>
If the school instead issued an OAuth Developer Key (third-party app access),
authorize in the browser with:
schoolbridge auth login --base-url <url> --client-id <id> --client-secret <secret>
— tokens then refresh automatically.
If the student can't create a token (some schools disable it; the mobile app
has no token button), fall back to the zero-credential calendar feed: have
them open Canvas in a web browser → Calendar → "Calendar Feed" (bottom-right)
→ copy the .ics URL, then run:
schoolbridge init --provider ics --feed-url <url>
This covers assignments, due dates, calendar events, ranking, and study
plans — but not grades, announcements, or feedback, so skip those features
and say why if asked.
The token/secret values are secrets — never repeat them back in conversation
or logs. For testing without credentials, add --provider mock to any
command to get realistic sample data.
Commands (add --json for machine-readable output)
schoolbridge upcoming --json [--days N]— work due in the next N days (default 7) across all courses, plus recent overdue unsubmitted work. Each item carriespriority(0–100) andpriorityLabel(critical/high/medium/low),status(unsubmitted/submitted/graded/missing/ overdue),dueInHours, points, and URLs.schoolbridge grades --json— current grade per course plus everything graded in the last two weeks with scores.schoolbridge announcements --json [--days N]— teacher announcements, newest first (default: last 14 days).schoolbridge assignment <courseId> <assignmentId> --json— one assignment with its full instructions as plain text. Use this before building a study plan.schoolbridge calendar --json [--days N]— upcoming course calendar events (review sessions, field trips, in-class tests; default: next 30 days).schoolbridge feedback --json [--days N]— teacher comments on the student's submitted work (default: last 14 days).schoolbridge events --json— everything that changed since the last check: new assignments, due-date changes, posted/changed grades, new announcements, new discussions, new or rescheduled calendar events, newly published course content and files, new teacher feedback, and course-grade moves. One JSON object per line; empty output means nothing new. The first run ever saves a baseline and prints nothing.
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.
- yesterday First seen · 96 lines · 66 tokens per session scan A 9162ff1b0f38
schoolbridge is a skill published in the GitHub repository Shoberman2/schoolbridge (0 stars, last pushed 15d ago), licensed MIT. It adds 66 tokens to every session and 1,180 once invoked, about $0.0003 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
canvas-grade-check
Check grade standing across Canvas courses and answer what-if questions like what score is needed on the final for an A. Use when the user asks about grades, GPA impact, whether they can still pass, or what they need on remaining work.
canvas-morning-check
Daily Canvas briefing — what's due soon, new announcements, unread messages, and newly posted grades or feedback across all courses. Use when the user asks what's going on with school today, wants a course catch-up, or says good morning and has coursework.
canvas-week-plan
Plan the week's coursework from Canvas — every deadline across courses, ordered and grouped by day, with what each task actually requires. Use when the user asks to plan their week, wants to know what's coming up, or asks how to schedule study time.
notebooklm
Programmatic access to Google NotebookLM for creating notebooks, adding sources (URLs, YouTube, PDFs, audio, video, images), chatting with content, generating artifacts (podcasts, videos, reports, quizzes, mind maps, flashcards, infographics), and downloading results. Includes capabilities beyond the web UI.
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis with two-column tables. Left column preserves the chapter content; right column maps every idea to the reader's actual life using brain context. Output is a single brain page at media/books/ -personalized plus an optional PDF via brain-pdf.
octave-literacy
LLM-native structured communication format. Teaches OCTAVE syntax rules, canonical forms, and warning prevention for zero-error .oct.md authoring.