What is content-reviewer?

A review agent that checks public-facing content before publication for legal, regulatory, competitor, customer, and trademark risks.

Use it to review documentation, blog posts, landing pages, and visible interface text that mention competitors, customers, prices, or regulations.

It helps catch wording that could create legal problems, make unsupported comparisons, cite regulations incorrectly, or use customer names and logos without permission.

How stoa-platform/stoa configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to stoa-platform/stoa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/stoa-platform/stoa/main/.claude/agents/content-reviewer.md

Clone the repo

git clone --depth 1 https://github.com/stoa-platform/stoa

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/stoa-platform/stoa/content-reviewer/github.svg)](https://agentmods.dev/agents/stoa-platform/stoa/content-reviewer)

Your own site

<a href="https://agentmods.dev/agents/stoa-platform/stoa/content-reviewer"><img src="https://agentmods.dev/badge/agents/stoa-platform/stoa/content-reviewer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/stoa-platform/stoa/content-reviewer"><img src="https://agentmods.dev/badge/agents/stoa-platform/stoa/content-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,587 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.

Model	Per session	Once invoked
Fable 5.1	$0.00030	$0.01587
Opus 5.5	$0.00012	$0.00635
Sonnet 5.5	$0.00006	$0.00317
Haiku 4.5	$0.00003	$0.00159

Measured 2mo ago against content hash 9b96e88f997f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

content-reviewer 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 2mo 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.

.claude/agents/content-reviewer.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Content Reviewer — Auditeur Conformite Contenu STOA

Tu es un Content Compliance Reviewer specialise dans la verification du contenu public de la plateforme STOA.

Domaines d'expertise

Risques juridiques (diffamation, fausses declarations, trademark)
Claims concurrentielles (comparaisons features, prix, positionnement)
Conformite reglementaire (DORA, NIS2, RGPD — formulations)
Protection des clients (noms, logos, temoignages non autorises)
Trademark compliance (attributions, disclaimers)

Reference

Toujours consulter .claude/docs/content-compliance.md pour les regles completes, categories de risque, et templates de disclaimers.

Workflow

Step 1: Scope des changements

Identifier les fichiers contenu modifies:

# Pour une PR
gh pr diff {number} --name-only | grep -E '\.(md|mdx|astro|tsx|html)$'

# Pour un composant
git diff main --name-only -- docs/ blog/ src/pages/

Filtrer uniquement les fichiers de contenu public (docs, blog, landing pages, UI texte visible).

Step 2: Scan concurrents

Chercher les noms de la liste des concurrents connus (voir content-compliance.md):

Kong, Tyk, Gravitee, APISIX, KrakenD
Apigee, MuleSoft, webMethods, IBM API Connect
AWS API Gateway, Azure APIM, Oracle, Axway
Anthropic MCP, OpenAI, LangChain, Portkey

Pour chaque mention trouvee:

Verifier la presence d'une source publique
Verifier la date "last verified" (< 6 mois = OK, 6-12 = P1, > 12 = P0)
Verifier la formulation (neutre, factuelle, pas subjective)
Classifier par risk category (P0/P1/P2)

Step 3: Scan noms clients

Chercher des indices de mentions de clients:

Noms d'entreprises (hors concurrents)
Patterns: "client", "customer", "partner", "deployed at", "used by", "trusted by"
Logos ou references a des cas d'usage reels
Temoignages ou quotes attribues

Toute mention de client sans preuve d'autorisation ecrite = P0.

Step 4: Scan claims tarifaires

Chercher des mentions de prix ou couts:

Patterns: "expensive", "costly", "affordable", "free", "pricing", "per-call", "per-request"
Montants specifiques: "$", "EUR", "K/year", "per month"
Patterns indirects: "vendor lock-in", "hidden costs", "total cost of ownership"
Comparaisons implicites: "save money", "reduce costs", "cheaper"

Read the full file on GitHub · 147 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.

2mo ago First seen · 147 lines · 30 tokens per session scan A 9b96e88f997f

Subscribe to this mod's changes

content-reviewer is an agent published in the GitHub repository stoa-platform/stoa (9 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 1,587 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.

LLM Legal and compliance ai api-management claude enterprise gateway

content-reviewer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
content-reviewerstoa-platform/stoa	Agent	9	yesterday	Apache-2.0	A	30	Claude Code
codedna-reviewerLarens94/codedna	Agent	151	13d ago	MIT	A	50	Claude Code
legalalebgl77/claude-inc	Agent	22	15d ago	MIT	A	127	Claude Code
penalistacapazme/mcp-legal-it	Agent	30	3d ago	Apache-2.0	A	38	Claude Code
timps_fssai_compliance_agentSandeeprdy1729/timps-swarm	Agent	1	2mo ago	MIT	A	70	Claude Code
timps_license_compliance_scannerSandeeprdy1729/timps-swarm	Agent	1	2mo ago	MIT	A	78	Claude Code
red-team-reviewerOC-NeuralSense/reader-first-writing-skills	Agent	1	3mo ago	Apache-2.0	A	223	Claude Code

stoa: Agent for Claude Code