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 adamwstauffer/shidler --skill recommendation-lettersgit clone --depth 1 https://github.com/adamwstauffer/shidlerWrote 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/adamwstauffer/shidler/recommendation-letters)<a href="https://agentmods.dev/skills/adamwstauffer/shidler/recommendation-letters"><img src="https://agentmods.dev/badge/skills/adamwstauffer/shidler/recommendation-letters/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/adamwstauffer/shidler/recommendation-letters"><img src="https://agentmods.dev/badge/skills/adamwstauffer/shidler/recommendation-letters.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 | $0.00139 | $0.01896 |
| Opus 5 | $0.00069 | $0.00948 |
| Sonnet 5 | $0.00028 | $0.00379 |
| Haiku 4.5 | $0.00014 | $0.00190 |
Grade A, and why
recommendation-letters 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 11d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recommendation Letters
Draft recommendation and reference letters for Adam W. Stauffer's students in his established house style, working only from verified facts.
Ground rule: verify, never invent (non-negotiable)
Every substantive claim in a letter must come from a source the student actually supplied — a grade from the gradebook/transcript, a fact from their résumé, an objective stated in their own words (email, personal statement). Never infer, estimate, or fabricate grades, GPAs, employers, job titles, dates, achievements, career goals, or motivations.
- If a needed fact is missing, leave a generic placeholder or ask the user — do not guess.
- Placeholders stay generic and descriptive:
<FIN 321 grade>,<student's stated objective>,<employer / role from résumé>. - Never write a specific value you have not verified, not even as a placeholder — e.g. never
<A+>, never a made-up firm or figure. A specific-looking placeholder reads as a real fact once the brackets are removed, which is exactly the failure this rule prevents. - This applies to characterizations too: don't assert a student "excelled" or was "top of the class" unless the record supports it.
When unsure whether something is verified, treat it as unverified.
Where things live
- Master template (canonical, fill-in):
assets/master-recommendation-template.docxin this skill. It holds the fixed scaffold (bio + signature verbatim), a paste-ready course block for every course Adam teaches (BUS 313 / 314 / FIN 321 / BUS 620 / BUS 629 / BUS 122B), purpose-line and closing-line menus, combo guidance, and style notes. Every fill-in is a generic<green field>. - Finished letters + student materials:
recommendations/<YYYY-MM>-<lastname>-<firstname>/at the repo root. This tree is gitignored (student PII); seerecommendations/README.md. Date = the letter's authored month. Multi-target applicants keep one folder with a file per school/employer. - Grades to fill
<course grade>fields come from the gradebook, not memory. Gradebooks are consolidated under each offering'signore/<YYYY-Season>/grades/. The*_FinalGrades_*.xlsxexports carry the letter grade in column P (and the numeric in column O); the plain*_Grades_*.csvexports carry only the number — convert those with the SSOT scale indocs/grading-scale.mdorscripts/grading/letter_grade.py(e.g.python scripts/grading/letter_grade.py 92→A-). Never guess a letter from a number — read column P or apply the scale.
What ships with it
2 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.
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.
- 11d ago First seen · 127 lines · 139 tokens per session scan A c71f809f9192
recommendation-letters is a skill published in the GitHub repository adamwstauffer/shidler (10 stars, last pushed 2d ago), licensed MIT. It adds 139 tokens to every session and 1,896 once invoked, about $0.0007 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
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…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
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.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.