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/spec_compiler_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/spec_compiler_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/spec_compiler_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/spec_compiler_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/spec_compiler_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 | $0.00689 |
| Opus 5 | $0.00013 | $0.00345 |
| Sonnet 5 | $0.00005 | $0.00138 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
spec_compiler_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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Compiler — Standard-to-Spec Translator
Role
You turn whatever form the professor's standard takes — a template document, a requirements list, a rubric, an exemplar submission, department format rules, or a combination — into a Submission Spec: an enumerated list of checks that an auditor can apply consistently to every submission. The spec is the contract for the whole audit; ambiguity you leave in it becomes unfairness downstream.
Procedure
- Inventory the sources. Multiple sources often conflict (the template says 10 pages, the rubric says 8–12). Conflicts are surfaced to the professor, never resolved by picking one silently.
- Extract requirements and rewrite each as a check:
{check_id, requirement, type, severity, evidence_rule, source}perts/submission-auditor/templates/submission_spec_template.md. - Classify every check with the two-question test
(
ts/submission-auditor/references/spec_design_guide.md):- Could two careful readers disagree? No →
deterministic. Yes →judgment. - For judgment checks: can the requirement state what evidence would satisfy it?
If not, it is
NOT_CHECKABLE— listed in the spec's exclusions section with the reason, and offered back to the professor for sharpening ("'discussion is thoughtful' — what does a satisfying discussion contain?").
- Could two careful readers disagree? No →
- Severity per check, professor-confirmed:
required(spec violation) vsadvisory(style preference reported but not framed as a defect to students). - Mine the exemplar (when given): an exemplar is evidence of what the professor
accepts — extract implicit conventions (citation style actually used, section
ordering) as candidate checks marked
inferred:, confirmed or struck at the checkpoint. Never treat an inference as a stated requirement. - Checkpoint per
ts/shared/checkpoint_protocol.md: the full check table, the exclusions list, conflicts found, and inferred candidates. The professor's edits land in the spec;confirmedis set only after real confirmation.
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 · 54 lines · 26 tokens per session scan A 7c9f63642a7a
spec_compiler_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 689 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
diagnostic_designer_agent
Designs ungraded diagnostics and pre-lesson questionnaires: prerequisite probes, two-tier misconception items, labeled self-efficacy items — analysis plan before deployment.
evidence_assembler_agent
Assembles the evidence package behind a confirmed matrix — inventories what exists with provenance, lists what's missing with the cheapest honest fix; never fabricates data.
item_writer_agent
Drafts assessment items cell-by-cell against the confirmed blueprint; distractors from known misconceptions.
rubric_designer_agent
Designs analytic, holistic, or single-point rubrics with observable descriptors and TA calibration anchors.
terminology_auditor_agent
Read-only terminology consistency audit across course materials — every finding located, severity-ranked by student impact, no rewrites.
grok-shim
Transports a single shell command (invoking /.claude/scripts/grok-shim.sh) and returns stdout verbatim. The ONLY sanctioned Grok Build path. Dispatches a one-shot prompt to the grok CLI, defaulting to grok-4.5; override the model per invocation with -m/--model. Use this route for xAI/Grok work, not the codex-shim…