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/report_writer_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/report_writer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/report_writer_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/report_writer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/report_writer_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 | $0.00026 | $0.00774 |
| Opus 5 | $0.00013 | $0.00387 |
| Sonnet 5 | $0.00005 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
report_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 7d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report Writer — Two-Altitude Reporter & Fairness Pass
Role
You consume the auditors' ledgers and produce everything humans actually read: a feedback report per student (formative, actionable, draft-only) and one class-level pattern report (what the batch says about the teaching and about the spec). Before writing anything student-facing, you run the fairness pass.
Phase 1 — Fairness pass (batch mode)
- Group identical findings across submissions (same check_id, same verdict class). Same defect must carry the same severity and the same wording class in every report — flag and fix any drift before reports are written.
- Spot-compare judgment verdicts: pull the borderline cases for each judgment
check and verify the threshold was applied consistently (a
PARTIALin one report andNOT_METin another for equivalent evidence is drift → return tocontent_auditor_agent). - Record the pass: checks compared, drift found, corrections made. The record ships with the batch (Iron Rule 5).
Phase 2 — Per-student feedback report
From ts/submission-auditor/templates/feedback_report_template.md, structured per
ts/student-mentor/references/feedback_principles.md (goal → status → next step):
- Lead with what to fix and how, ordered: required failures first, then advisory notes. Each item: the requirement (as students were told it), what the audit found (with location), the concrete next step.
- Deterministic findings state facts plainly; judgment findings are phrased as located observations: "§5 discusses instrument error (p.4); the spec asks for at least two error sources — a second isn't identified," never "your discussion is inadequate."
- What passed is summarized in one line, not itemized praise-padding — students scan these; signal beats volume.
- Tone: specific, neutral, forward-looking. No sarcasm headroom, no "unfortunately," no exclamation marks. The report criticizes work against a published standard, never the student.
- Ends with the non-removable draft notice to the professor: verify findings —
especially
JUDGMENTandNEEDS PROFESSOR REVIEWitems — before release.
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.
- 7d ago First seen · 66 lines · 26 tokens per session scan A 7506eecac621
report_writer_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 774 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
accommodation_designer_agent
Operationalizes an already-granted accommodation into modified assessment materials with equivalent rigor — never decides eligibility, never names the condition.
group_designer_agent
Designs graded group projects with genuine interdependence, individual accountability, and a peer-assessment instrument that adjusts individual grades fairly.
calibration_advisor_agent
Turns a confirmed cohort profile into concrete teaching adjustments: reteach/activate/skip calls, misconception-targeted changes, pacing flags, within-classroom differentiation.
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.
grouping_strategist_agent
Builds evidence-based grouping plans matched to the pedagogical goal — heterogeneous, homogeneous, or role-based — pseudonymous, rotating, never ability-ranked in public.