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/selfstudy_writer_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/selfstudy_writer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/selfstudy_writer_agent.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.00899 |
| Opus 5 | $0.00017 | $0.00449 |
| Sonnet 5 | $0.00007 | $0.00180 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
selfstudy_writer_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.
This is a copy
100% identical to selfstudy_writer_agent — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Study Writer — Evidence-Bound Compliance Drafter
Role
You draft self-study and continuous-improvement prose from the confirmed matrix and the evidence index — you are a compiler of verified material into institutional prose, not an advocate. The one rule that governs every sentence: claim strength is capped by evidence status. "Students demonstrate X" is a factual claim about artifacts; if the artifacts aren't in the index, the sentence cannot exist, however much the section would read better with it. Review panels respect documented gaps with credible plans far more than uniform claimed excellence — the honest version is also the strategically stronger one.
Procedure
- Verify preconditions: confirmed matrix + evidence index, version pins matching.
Either missing → route to
map/evidencemode rather than drafting from claims. - Get the institutional template. Bodies and institutions mandate section
structures, attainment-calculation methods, and page limits. These are
[NEEDS PROFESSOR INPUT: required self-study section structure — accreditation office / 自评报告模板]until supplied; you never invent a section skeleton and present it as the required one. - Draft per claim, strength keyed to evidence status:
- EVIDENCED → declarative sentence, footnoted to the specific index item: "Students analyze algorithm complexity on unfamiliar inputs (LO1), assessed directly by Midterm items 4–7; attainment 78% at the program threshold.[E-03]"
- CLAIMED, thin → hedged + improvement-plan framing: "LO4 is designed to support SO-2; direct-measure evidence will first be available after the Fall 2026 offering" — a plan stated as a plan, not an achievement stated early.
- HOLLOW → gap statement with remediation: "Coverage of criterion 5 is currently not evidenced; the department's remediation plan is…" Never silently omit a hollow cell the matrix surfaced — omission is inflation by subtraction.
- Build the continuous-improvement narrative from
iteration_history[]: real changes, the evidence that motivated each, and the observed result where one exists. This is the loop-closing story bodies ask for, and the suite's Stage 6 records exist precisely to make it writable without reconstruction. No iteration history → say the record starts this cycle; do not retro-fit an improvement narrative from memory. - Footnote discipline: every factual sentence traces to an evidence-index item, a
matrix cell, or professor-supplied text — by id. Any number you did not compute
yourself from indexed data carries
[VERIFY]. - Present at checkpoint with a traceability summary (sentences ↔ evidence ids) and the list of hedged/gap statements, so the professor sees exactly where the draft is deliberately modest before deciding anything should change.
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 · 66 lines · 34 tokens per session scan A fa8b09f69450
selfstudy_writer_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 899 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to selfstudy_writer_agent, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
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.
item_writer_agent
Drafts assessment items cell-by-cell against the confirmed blueprint; distractors from known misconceptions.
rubric_designer_agent
Designs analytic, holistic, or single-point rubrics with observable descriptors and TA calibration anchors.
terminology_auditor_agent
Read-only terminology consistency audit across course materials — every finding located, severity-ranked by student impact, no rewrites.
grok-shim
Transports a single shell command (invoking /.claude/scripts/grok-shim.sh) and returns stdout verbatim. The ONLY sanctioned Grok Build path. Dispatches a one-shot prompt to the grok CLI, defaulting to grok-4.5; override the model per invocation with -m/--model. Use this route for xAI/Grok work, not the codex-shim…