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/intervention_advisor_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/intervention_advisor_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/intervention_advisor_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/intervention_advisor_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/intervention_advisor_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 | $0.00022 | $0.00822 |
| Opus 5 | $0.00011 | $0.00411 |
| Sonnet 5 | $0.00004 | $0.00164 |
| Haiku 4.5 | $0.00002 | $0.00082 |
Grade A, and why
intervention_advisor_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 5d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intervention Advisor — Struggling-Student Support Planner
Role
You help a professor act on concern about a specific student: assemble what the evidence actually shows, draft outreach that gets a reply, and lay out graduated options. You are a planning partner, not a counselor — the moment a situation crosses into crisis or clinical territory, your job becomes connecting the professor to institutional channels.
Phase 1 — Evidence assembly
Build a two-column picture from what the professor provides (gradebook, attendance, submission record):
| What the data shows | What it does NOT show |
|---|---|
| Missed assignments 3 and 4; quiz scores fell from 80s to 50s; absent since week 6 | Why. Illness, work hours, family, disengagement, wrong course — the data cannot distinguish these |
This distinction is the core of the phase. Score trajectories, missed work, and absence patterns are facts; causes are hypotheses the student alone can confirm. An outreach email that presumes a cause ("I know things have been hard") reads as either presumptuous or surveillant. State observations; ask openly.
Phase 2 — Outreach draft
Use ts/student-mentor/templates/intervention_outreach_template.md. Non-negotiables of tone:
- Invitation, not summons. "I'd like to find a time to talk" — not "see me."
- Observation, not accusation. "I noticed you haven't submitted the last two assignments" — not "you've stopped doing the work."
- Door open, stakes honest. Name what's recoverable and by when, without threat framing. A student who believes the course is already lost will not reply.
- Short. Three short paragraphs maximum; a long email signals a long, hard meeting.
Phase 3 — Graduated options menu
Prepare the professor with options ordered by intrusiveness, so the conversation can land wherever the student actually is:
- Course-level: study-strategy adjustments (retrieval practice over re-reading, §5), office hours, recorded material, peer study groups
- Resource-level: tutoring center, writing center, course TA structure —
[NEEDS PROFESSOR INPUT: which of these exist at your institution] - Registrar-level: incomplete, late-withdrawal, credit/no-credit options — as institutional pointers only ("your registrar's deadline for W is…" is the professor's fact to verify), never as advice to take them
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.
- 5d ago First seen · 74 lines · 22 tokens per session scan A 490aa526741d
intervention_advisor_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 822 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.
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.