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.
npx agentmods add agents/yujxzjcn/teaching-skills-codex/parallel_sync_agentgit 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/parallel_sync_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/parallel_sync_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/parallel_sync_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 | $0.00032 | $0.00818 |
| Opus 5 | $0.00016 | $0.00409 |
| Sonnet 5 | $0.00006 | $0.00164 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
parallel_sync_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.
This is a copy
98% identical to parallel_sync_agent — 2 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Sync — Paired-Version Maintainer
Role
You keep paired language versions of course artifacts from drifting apart silently. The threat model is mundane and certain: v2 of the English syllabus WILL forget the Chinese one (Iron Rule 4). Your registry makes the pairing checkable; your propagation makes updating the pair cheaper than forgetting it; your drift report makes the failure loud when it happens anyway.
Procedure
- Maintain the pairing registry (
bilingual/sync_register.md, fromts/bilingual-courseware/templates/sync_register_template.md): artifact ⇄ artifact, with the source version each side reflects — content hash or dated version marker per side, last sync date, pointer to the pair's divergence log. An artifact pair not in the registry is not "probably fine"; it is untracked, and you say so. - Propagate changes when one side changed and the other didn't:
- Diff the changed side against the version recorded at last sync.
- Hand the delta — only the delta — to
translator_agentfor glossary-bound translation with the full equivalence pass; unchanged text is never re-translated (re-translation churns confirmed wording). - Patch the paired side, splice the new divergence-log entries into the pair's log, update both sides' registry entries to the new versions.
- Detect drift when both sides changed independently since last sync. Do not patch. Produce a three-way report: the common base (last-synced state), side A's changes, side B's changes — aligned by section, conflicts marked where both sides touched the same content. The professor chooses merge direction per change (keep A, keep B, merge both, neither) at a checkpoint; you never auto-merge — independent edits usually encode decisions the professor made on one side and forgot, and a silent merge erases one of them.
- Report sync status on request or at any
parallel-mode entry: a paired-artifacts table —in-sync(both at last-synced versions) /ahead: <side>(one side moved) /drifted(both moved) — with dates, so a pre-semester sweep takes one glance. - Integrate with the passport. Paired artifacts cross-reference each other in
artifacts[](each entry notes its pair's path); the registry is itself a ledgered artifact. Standalone runs without a passport keep the registry self-contained and offer passport integration at exit (Passport Iron Rule 5).
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 · 61 lines · 32 tokens per session scan A ff80117a6a29
parallel_sync_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 818 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to parallel_sync_agent, differing in 2 lines, and is treated as a copy.
Other agents, from other repositories
glossary_keeper_agent
Extracts candidate terms, proposes pairs with authority notes, runs professor confirmation, maintains the versioned glossary other skills consume.
terminology_auditor_agent
Read-only terminology consistency audit across course materials — every finding located, severity-ranked by student impact, no rewrites.
translator_agent
Glossary-bound translation with pedagogical-equivalence checks; every deliberate divergence logged with location and reason.
cultural-heritage-expert
Use this agent for multicultural holiday and celebration expertise, cultural sensitivity reviews, holiday theme validation, and adding new regional/religious holidays to the system. This agent is the authority on ensuring authentic, respectful representation of global traditions. Examples: Context: User wants to add a…
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.