standards_analyst_agent

standards_analyst_agent is an agent for Claude Code from YujxZJCN/teaching-skills-codex. It costs 34 tokens per session (880 once invoked), scanned A, a copy of standards_analyst_agent, MIT.

A criteria-register builder for accreditation standards, program outcomes, and institutional review rubrics. It records the supplied wording exactly and notes what evidence each criterion requires.

In plain words
What is it for?
It identifies the standard and version, structures the professor's criteria, records required evidence types, and marks criteria that need clarification.
Why use it?
It gives later mapping work a clear target without silently replacing missing or outdated standards with generic examples. It flags missing versions, source text, and vague criteria.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit It identifies the standard and version, structures the professor's criteria, records required evidence types, and marks criteria that need clarification.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/yujxzjcn/teaching-skills-codex/standards_analyst_agent
Install

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.

Clone the repo
git clone --depth 1 https://github.com/YujxZJCN/teaching-skills-codex

Made for: Claude Code.

Wrote 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.

agentmods badge for standards_analyst_agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/standards_analyst_agent/github.svg)](https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/standards_analyst_agent)
Your own site
<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.

agentmods 80×15 button for standards_analyst_agent

Your own site · 80×15
<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>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 880 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 94% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 9ee022fd51b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

Origin

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.

skills/teaching-suite/ts/accreditation-mapper/agents/standards_analyst_agent.md · 66 lines

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

  1. 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.
  2. 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 generated
    • text — 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 in ts/accreditation-mapper/references/accreditation_frameworks.md; where the criterion itself is silent, record your reading as a proposal for the professor to confirm
    • measurability_notes — what would count as evidence, and at what grain (course level, program level, cohort level)
  3. 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.
  4. 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.
  5. 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.

Read the full file on GitHub · 66 lines

Changes

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.

  1. 9d ago First seen · 66 lines · 34 tokens per session scan A 9ee022fd51b4

Subscribe to this mod's changes

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.