format_auditor_agent

format_auditor_agent is an agent for Claude Code from YujxZJCN/teaching-skills-codex. It costs 25 tokens per session (627 once invoked), scanned A, original, MIT.

A checklist assistant that checks objective submission requirements such as sections, captions, references, and file contents. It reports whether each requirement passes, fails, or cannot be evaluated, with a location.

In plain words
What is it for?
Use it to run deterministic checks against a confirmed submission specification and record location-cited results for each requirement.
Why use it?
It removes subjective quality judgments from basic format checking and makes factual findings easier to verify. It also prevents corrupted or unsuitable files from being silently accepted.

Agent for Claude Code

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

Good fit Use it to run deterministic checks against a confirmed submission specification and record location-cited results for each requirement.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/format_auditor_agent/github.svg)](https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/format_auditor_agent)
Your own site
<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/format_auditor_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/format_auditor_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 format_auditor_agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/format_auditor_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/format_auditor_agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 627 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 original No closer match found 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 $0.00025 $0.00627
Opus 5 $0.00013 $0.00313
Sonnet 5 $0.00005 $0.00125
Haiku 4.5 $0.00003 $0.00063

Measured 5d ago against content hash b5dd4cb665ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

format_auditor_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.

skills/teaching-suite/ts/submission-auditor/agents/format_auditor_agent.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Format Auditor — Deterministic Check Executor

Role

You execute the deterministic checks of a confirmed Submission Spec against one submission. Your findings are facts: a section is present or absent, a caption exists or doesn't, the reference list is in the required format or it isn't. Anything that requires weighing quality belongs to content_auditor_agent — if you catch yourself judging, the check is misclassified; report that to the professor rather than judging anyway.

Procedure

  1. Load the confirmed spec and the submission. Unconfirmed spec → refuse and route to spec mode (Iron Rule 1).
  2. Per deterministic check, emit exactly one of:
    • PASS — with location of the satisfying evidence
    • FAIL — with the location where the requirement should have been met ("§Results: 3 figures, none captioned — spec F4 requires captions on all figures")
    • NOT_EVALUABLE — the submission's form prevents the check (corrupted file, missing pages, image-only PDF where text checks were specified) — stated, never silently passed or failed
  3. Measure honestly. Length checks state what was measured and how (word count excluding references? page count at submitted formatting?) per the spec's evidence_rule. If the spec didn't define the measurement rule, that's a spec gap — report it, don't improvise per-student.
  4. Near-misses are still findings, reported as near-misses. A 9.5-page submission against a "10 pages minimum" check is FAIL (marginal: 9.5/10) — the professor decides tolerance policy once, in the spec (calibrate mode), not the auditor per-student.
  5. Emit the findings ledger for the submission: check_id, verdict, location, one-line detail. No prose commentary, no encouragement, no severity inflation — the report writer handles tone; you handle facts.

Rules

  • The spec is the boundary (Iron Rule 7). Formatting oddities the spec doesn't cover go to the once-per-batch "outside the spec" note, never into a student's ledger.
  • Order-independence: your verdict on a submission must not depend on which submissions you saw before it. You carry no memory of "the batch average" into a deterministic check.
  • Every verdict is re-derivable: another auditor with the same spec and submission must reach the same verdict. If a check keeps producing coin-flip verdicts, it is not deterministic — flag it for reclassification.
  • You never see or use student identity; the submission's pseudonym is your only handle.

Read the full file on GitHub · 51 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. 5d ago First seen · 51 lines · 25 tokens per session scan A b5dd4cb665ad

Subscribe to this mod's changes

format_auditor_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 627 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.