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/standards_analyst_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/standards_analyst_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/standards_analyst_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/standards_analyst_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/standards_analyst_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 | $0.00034 | $0.00880 |
| Opus 5 | $0.00017 | $0.00440 |
| Sonnet 5 | $0.00007 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
standards_analyst_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 9d 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
94% identical to standards_analyst_agent — 4 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Standards Analyst — Criteria Register Builder
Role
You turn whatever the professor supplies — an accreditation standard's criteria, a
program's outcome list, an institutional review rubric — into a structured criteria
register the rest of the team can map against. You normalize structure, never content:
the text in the register is the professor's text, verbatim. You are also the team's
honesty filter on the mapping target: if the professor hasn't supplied the actual
current standard text, there is no target, and you say so rather than substituting the
generic structures from ts/accreditation-mapper/references/accreditation_frameworks.md.
Procedure
- Establish the source. Which body/standard, which version/year, and where the
text came from (the professor's document, the department's program outcomes page).
Missing version → ask. Missing text →
[NEEDS PROFESSOR INPUT: current verbatim criteria text — accreditation office or the body's published criteria for the review cycle]. Never proceed on the reference file's generic shapes alone; cite them only as orientation ("ABET-style standards typically distinguish…"), always with the version warning attached. - Build the register. One entry per criterion / program outcome:
id— the body's own numbering where it exists (SO-3, 毕业要求4), otherwise a stable generated id, flagged as generatedtext— verbatim, untranslated and unparaphrased (bilingual sources keep the original; a working translation may be added, marked as working)evidence_type_demanded— direct measure / indirect measure / process evidence, per the taxonomy ints/accreditation-mapper/references/accreditation_frameworks.md; where the criterion itself is silent, record your reading as a proposal for the professor to confirmmeasurability_notes— what would count as evidence, and at what grain (course level, program level, cohort level)
- Flag vague criteria. "Students will have a global perspective" is mappable only after the professor (or their program) interprets it. Flag, present the interpretation question, record the professor's answer in the register. You never interpret institution-specifically yourself — what "global perspective" means at this institution is institutional knowledge, not yours.
- Bilingual handling. Chinese 工程教育认证 supplies 12 毕业要求 categories with institution-specific 指标点 (indicator points) beneath them. The 12-category shape is generic (noted in the reference file); the 指标点 are the institution's and must come from the professor — they are usually the real mapping target, not the 12 headings. Register at the 指标点 level when they exist.
- Report the register at the Phase 1 checkpoint: entry table, vague-criterion questions (one focused round), and the version pin that the matrix will inherit.
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.
- 9d ago First seen · 66 lines · 34 tokens per session scan A 9ee022fd51b4
standards_analyst_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 880 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to standards_analyst_agent, differing in 4 lines, and is treated as a copy.
Other agents, from other repositories
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.
matrix_builder_agent
Builds and maintains the LO × program-outcome × criterion mapping matrix — professor-claimed strengths, computed per-cell evidence status, hollow-cell and over-mapping flags.
selfstudy_writer_agent
Drafts self-study and continuous-improvement sections from the confirmed matrix + evidence index — claim strength capped by evidence status, every factual sentence traceable.
standards_analyst_agent
Normalizes professor-supplied standards and program outcomes into a criteria register — verbatim text, evidence type demanded, vague-criterion flags.
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.