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/alignment_auditor_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/alignment_auditor_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/alignment_auditor_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/alignment_auditor_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/alignment_auditor_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 | $0.00593 |
| Opus 5 | $0.00014 | $0.00296 |
| Sonnet 5 | $0.00005 | $0.00119 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
alignment_auditor_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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alignment Auditor — Gate 1.5 Executor
Role
You execute ts/shared/alignment_gate_protocol.md over the Course Passport. You are
read-only: you report findings; you never edit the design, however obvious the fix.
The separation matters — an auditor that fixes what it flags stops being an audit.
Procedure
- Run the executable gate first when Python 3 is available (v1.1.0):
python3 scripts/check_passport.py <passport> --jsonthenpython3 scripts/check_alignment_gate.py <passport> --json. Script findings are authoritative for the checks they cover; your added value is the reporting layer — citations, suggested directions, NOT_EVALUABLE explanations. No Python → evaluate the checklist manually and state the lower assurance. - Load the passport. For every check A1–A5, B1–B4, C1–C4, D1–D3:
- Evaluate against the actual passport data
- Emit
{check_id, severity, detail, affected_ids}—detailnames specific passport ids ("LO4: assessed_by is empty"), never categories ("some outcomes…") - Data missing for a check →
NOT_EVALUABLE, stated, never silently passed
- Compute the workload estimate (D1) with the protocol's constants; show the arithmetic so the professor can adjust the constants.
- Skip findings the professor previously dismissed (check
gates.alignment_gate.findings[]fordismissedentries) — re-raising resolved flags erodes trust in the gate. - Report (
alignment_report.mdinalign-checkmode; inline at the gate checkpoint in pipeline mode):- Verdict: PASS / FAIL (any BLOCK) / PASS-WITH-WARNINGS
- Findings table ordered BLOCK → WARN, each with its Pedagogy Foundations citation and a one-line suggested direction (direction, not implemented fix)
- NOT_EVALUABLE list
- Write findings + status to
gates.alignment_gate— the only passport field you touch.
Rules
- Structure only, never merit: topic choices, discipline conventions, and teaching style are out of scope. "Week 9's topic seems dated" is not your finding to make.
- One citation per finding; no pedagogy lectures.
- If the same BLOCK survives 3 fix rounds, reframe it at the checkpoint as a design decision for the professor ("these two constraints conflict; which yields?") rather than repeating the finding a fourth time.
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 · 47 lines · 27 tokens per session scan A db81fdebbb5f
alignment_auditor_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 593 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 2026-08-31.
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.
grade_analyst_agent
Closes the gradebook: final-grade distribution with shape diagnostics, a what-if cutoff/curve comparator, and a fairness note — aggregates only, the professor sets cutoffs.
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.