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 psd401/psd-claude-plugins --skill enrollmentgit clone --depth 1 https://github.com/psd401/psd-claude-pluginsWrote 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/psd401/psd-claude-plugins/enrollment)<a href="https://agentmods.dev/skills/psd401/psd-claude-plugins/enrollment"><img src="https://agentmods.dev/badge/skills/psd401/psd-claude-plugins/enrollment/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/psd401/psd-claude-plugins/enrollment"><img src="https://agentmods.dev/badge/skills/psd401/psd-claude-plugins/enrollment.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 | $0.00023 | $0.10853 |
| Opus 5.5 | $0.00009 | $0.04341 |
| Sonnet 5.5 | $0.00005 | $0.02171 |
| Haiku 4.5 | $0.00002 | $0.01085 |
Grade A, and why
enrollment scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf -X POST "$ENROLLMENT_NOTIFY_URL" \ How it starts
The opening of the file, as written. The whole thing — 528 lines — stays where its author put it; the contents beside it link to each section on GitHub.
P223 Enrollment Automation
You orchestrate Peninsula School District's monthly P223 enrollment reporting process. This skill automates report generation from PowerSchool, validates enrollment data, and flags issues for human review.
Human-in-the-loop: This tool surfaces issues, flags discrepancies, and prepares files. Humans make judgment calls and submit to EDS.
Portability Rules — READ FIRST
This skill runs on multiple machines (Hagel's laptop, the office Mac mini on a schedule, and potentially another user's machine in the future). Every action must be machine-agnostic:
- All skill files are referenced relative to THIS skill's directory (the directory containing this SKILL.md). Never use repo-relative paths like
plugins/psd-productivity/...— on an installed machine the plugin lives under~/.claude/plugins/marketplaces/, not in a checkout. - Local staging directory:
~/Enrollment/P223-<Month>-<Year>/(e.g.~/Enrollment/P223-September-2026/). Never use~/Desktop. - Google Drive is the home of record. Local files are staging only — every report must be uploaded to the Drive BACKUP folder before the month is DONE. A run finished on the mini must be fully retrievable from any other machine.
- Shared state lives in the tracking sheet, not on any one machine:
- P223 Enrollment Tracking 2026-2027:
1t10gPECTUd2s9kMrm2jsOIvMHKnRpTcbhJGq-hO7Yg0 - Tabs:
Calendar(count dates,ReminderDate, andRerunDate— a date inRerunDatemakes the nextdaily-checkon that day run the month in rerun mode),SchoolStatus(per school per month),DistrictStatus(per month phases; cols I/J written by theeds_submittedwebhook event, cols L/MFindingsDoc/CompletionEmailSentwritten by thecollection_completeevent). Notification addresses live ONLY in the live n8n workflow — never in this skill, the sheet, or any committed file - Read/write via
gwsCLI,valueInputOption=RAWalways
- P223 Enrollment Tracking 2026-2027:
- Saving rendered reports: there is no print-to-PDF. The page serializer in
references/report-checklist.md(in-page JavaScript through Claude in Chrome) downloads each rendered report as a self-contained<name>.htmlto~/Downloads;mvit into the month folder and upload it to Drive as a Google Doc (the Student Schedule Report included). The only PDFs are PowerSchool's own: the P223 form page and the Class Attendance Audit. - New machine? Follow
references/machine-setup.md— Chrome + the Claude in Chrome extension, two Chrome download settings, one-time PowerSchool login by a person,gwsauth, bun/uv.
What ships with it
21 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/BUILD-PLAN.md 12 KB
- references/cant-automate.md 4.2 KB
- references/fte-rules.md 6.3 KB
- references/known-exclusions.csv 502 B
- references/machine-setup.md 7.4 KB
- references/p223-process.md 7.6 KB
- references/report-checklist.md 30 KB
- references/school-config.md 8.9 KB
- scripts/ale_reconciler.py 14 KB runs code
- scripts/compare_runs.py 2.3 KB runs code
- scripts/district_checks.py 16 KB runs code
- scripts/drive_layout.py 4.9 KB runs code
- scripts/eds_txt.py 9.0 KB runs code
- scripts/enrollment_validator.py 15 KB runs code
- scripts/entry_exit_balancer.py 11 KB runs code
- scripts/findings_doc.py 15 KB runs code
- scripts/fte_calculator.py 14 KB runs code
- scripts/month_comparison.py 11 KB runs code
- scripts/rs_reconciler.py 13 KB runs code
- scripts/split_p223.py 4.8 KB runs code
- scripts/validation_report.py 15 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.
- 14d ago Changed · -1 lines 073f07331fc6
- 26d ago Changed · -22 lines 9d8adc110b65
- 1mo ago Changed 236e2ee07ae8
- 1mo ago Changed 361ff73cb065
- 1mo ago Changed 861747e19b2a
- 1mo ago Changed · +2 lines 4b1ed742acbb
- 1mo ago Changed · +64 lines 83277ef3708d
- 1mo ago Changed · +5 lines e7f43964dddf
- 2mo ago Changed · +91 lines 2d4107736f90
- 2mo ago First seen · 389 lines · 23 tokens per session scan A 66f22a728522
enrollment is a skill published in the GitHub repository psd401/psd-claude-plugins (2 stars, last pushed 9d ago), licensed MIT. It adds 23 tokens to every session and 10,853 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.