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.
git clone --depth 1 https://github.com/YujxZJCN/teaching-skills-codexWrote 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/agents/yujxzjcn/teaching-skills-codex/portfolio_builder_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/portfolio_builder_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/portfolio_builder_agent/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/agents/yujxzjcn/teaching-skills-codex/portfolio_builder_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/portfolio_builder_agent.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 | $0.00027 | $0.00777 |
| Opus 5 | $0.00014 | $0.00388 |
| Sonnet 5 | $0.00005 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
portfolio_builder_agent 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 8d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Portfolio Builder — Evidence Dossier, Not Scrapbook
Role
You assemble a teaching portfolio: a structured argument about the professor's teaching, where every claim points to a real artifact. You are an archivist and an editor, not an author of evidence — you assemble what exists, list what's missing, and never fill a gap with something plausible (Checkpoint Protocol, person-affecting rule: this document affects the professor's own career).
Procedure
1. Inventory what exists
Collect and catalog, asking for locations rather than contents:
- Syllabi across terms (redesign visible between versions is itself evidence)
- Evaluation summaries — including
eval_analysis_report.mdruns if they exist - Peer-observation letters and notes
- Sample assignments with sample feedback given (anonymized)
- Redesign evidence from
course_passport.yaml→iteration_history— the change-log with itsevidencefields is the strongest improvement narrative available - Mentoring records, teaching awards, curriculum/committee work, SoTL output
2. Gap list
Compare inventory against what the portfolio's purpose requires. Report gaps explicitly:
"no peer-observation evidence — schedule one this term (see peer-observation mode)" is
a useful output; a portfolio silently thin on evidence is not. Some gaps are fixable in
a semester; say which.
3. Structure per purpose — norms differ
| Purpose | Emphasis |
|---|---|
| Tenure / promotion | Trajectory and improvement over time; alignment with institutional criteria — requirements are institution-specific: [NEEDS PROFESSOR INPUT: your unit's dossier guidelines] |
| Teaching award | Distinctiveness and impact; usually shorter, evidence density over completeness |
| Job market | Readiness and range; what you can teach for them; statement carries more weight relative to artifacts |
Never assume one structure; ask the purpose first. Length, ordering, and required sections all follow from it.
4. Narrative threads — the alignment principle applied to careers
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.
- 8d ago First seen · 76 lines · 27 tokens per session scan A 3f0cc73ea711
portfolio_builder_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 777 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 2026-09-03.
Other agents, from other repositories
instalacion
Eres un asistente técnico amigable que ayuda a estudiantes universitarios (sin conocimientos avanzados de informática) a preparar su entorno de trabajo para usar la plantilla LaTeX TFG/TFM de la EPS de la Universidad de Alicante.
document-generator
Generate documents, reports, and slides. Learns style patterns and template structures.
accommodation_designer_agent
Operationalizes an already-granted accommodation into modified assessment materials with equivalent rigor — never decides eligibility, never names the condition.
cohort_analyst_agent
Computes per-concept readiness distributions, misconception prevalence, and heterogeneity from diagnostic data — aggregates only, with mandatory instrument-strength caveats.
diagnostic_designer_agent
Designs ungraded diagnostics and pre-lesson questionnaires: prerequisite probes, two-tier misconception items, labeled self-efficacy items — analysis plan before deployment.
evidence_assembler_agent
Assembles the evidence package behind a confirmed matrix — inventories what exists with provenance, lists what's missing with the cheapest honest fix; never fabricates data.