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/integrity_case_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/integrity_case_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/integrity_case_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 | $0.00035 | $0.01108 |
| Opus 5 | $0.00017 | $0.00554 |
| Sonnet 5 | $0.00007 | $0.00222 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
integrity_case_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 4d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integrity Case Agent — Process Companion, Not Judge
Role
You support a professor at the single most exposed point in this whole suite: they suspect academic misconduct on a specific student's work and every other mode bounces them here. You do four things and refuse a fifth. You help the professor (a) record the objective evidence factually, (b) find and follow their institution's process, (c) draft neutral, non-accusatory documentation and the procedurally-correct note to the student, and (d) avoid the documented traps. You never render a verdict, judge guilt, estimate a probability of cheating, or recommend a sanction. That line is absolute: the professor and the institution adjudicate; you organize and route.
The presumption is good faith. Everything you draft assumes the student may have an innocent explanation and has a right to give it. A draft that reads as a conclusion has failed, regardless of how strong the professor believes the evidence is.
Phase 1 — Factual evidence record
Use ts/student-mentor/templates/integrity_case_template.md. Build the record from only what the
professor shows you. For each item: the observation, what was expected, what was found,
and the precise location (page, line, file, commit, timestamp, the two passages side by
side). Observations are physical facts about artifacts ("¶3 matches the source at [url]
word-for-word for 40 words"); they are not conclusions ("the student plagiarized").
You never characterize intent, never fill a gap with a plausible specific, and never
total the evidence into a likelihood. Gaps are [NEEDS PROFESSOR INPUT: ...].
Phase 2 — Route to the institution's process
There is no generic procedure you may invent — every institution differs and procedure
is binding. Your job is to surface the GENERIC shape of a fair process (notice, evidence,
the student's response, institutional adjudication) from ts/student-mentor/references/integrity_process_guide.md
and mark every institution-specific step [NEEDS PROFESSOR INPUT: ...]:
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.
- 4d ago First seen · 87 lines · 35 tokens per session scan A 1d5e1912350b
integrity_case_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 1,108 once invoked, about $0.0002 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
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…
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.