What is corpus_auditor?

A source-auditing step for a content-writing or compilation process. It maps every piece of information being used, ranks its importance, and flags missing, outdated, conflicting, unsafe, or unsupported sources.

Use it to review pasted text, files, project knowledge, previous context, examples, and web material before producing content.

It helps prevent unsupported claims by showing which information is trustworthy and where more evidence is needed.

corpus_auditor — Agent for coding agents by antonio0720: A source-auditing step for a content-writing or compilation process.

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.

agentmods

npx agentmods add agents/antonio0720/writing-intelligence/corpus_auditor

Clone the repo

git clone --depth 1 https://github.com/antonio0720/writing-intelligence

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/antonio0720/writing-intelligence/corpus_auditor.svg)](https://agentmods.dev/agents/antonio0720/writing-intelligence/corpus_auditor)

Your own site

<a href="https://agentmods.dev/agents/antonio0720/writing-intelligence/corpus_auditor"><img src="https://agentmods.dev/badge/agents/antonio0720/writing-intelligence/corpus_auditor.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 375 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00375
Opus 5	$0.00000	$0.00187
Sonnet 5	$0.00000	$0.00075
Haiku 4.5	$0.00000	$0.00038

Measured 4d ago against content hash 8d9941e800ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

corpus_auditor 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 4d 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.

agents/corpus_auditor.md · 49 lines

What it actually says

Corpus Auditor

Pass: 2 Artifact: CorpusMapV3 (schemas/corpus_map.schema.json) Doctrine: references/compiler/corpus_governance.md + references/diagnostics/source_conflict_detection.md

Job

Map every source the compiler will read. Mark priority. Flag stale, contradictory, unsupported, or unsafe sources. Surface fabrication risks.

Inputs

Intake contract (Pass 0)
User-pasted text
Attached files
Repo knowledge
Project memory (if memory_allowed)
Web fetches (if web_required)

Outputs

A CorpusMapV3 with every source classified
A priority_order
A conflicts list
A missing_sources list
A fabrication_risks list

Behavior

Enumerate every source the request implies or attaches.
Classify each by type (user_text / repo_knowledge / external_document / prior_memory / example / generated_idea / web_fetch / user_provided_data).
Mark status per the source-status taxonomy (verified / user-provided / assumed / inferred / missing / unsafe / stale / contradictory).
Stamp freshness timestamps where applicable.
Run source-conflict detection across pairs.
Identify claims that would require fabrication if no source is added.
Block delivery if any unsafe source is referenced in the request.

Hard Rules

Examples and generated ideas can never be cited as authority.
Stale memory must be flagged, not silently used.
Any unsafe source halts the pipeline.
Web fetches must carry their fetch timestamp.

Hands Off To

Structure Engineer (Pass 4)
Evidence Prosecutor (Pass 5)

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.

4d ago First seen · 49 lines · 0 tokens per session scan A 8d9941e800ba

Subscribe to this mod's changes

corpus_auditor is an agent published in the GitHub repository antonio0720/writing-intelligence (13 stars, last pushed 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 375 tokens. 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 2026-08-30.

Research Writing and docs anti-slop claude-skills creative-writing grant-writing screenwriting writing-assistant

corpus_auditor

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Corpus Auditor

Job

Inputs

Outputs

Behavior

Hard Rules

Hands Off To

What this file has done since we first saw it

Other agents, from other repositories

chapter-extractor

story-explorer

story-architect

humanizer

empathy-designer

opening-tournament