What is bulwark-standards-reviewer?

A standards checker for Claude Code assets such as skills, agents, hooks, commands, integrations, and plugins. It compares them with official Anthropic requirements and reports severity-rated findings.

Use it to validate new or edited Claude Code assets, receive remediation suggestions, and get a structured pass-or-fail report.

It identifies invalid fields, locations, syntax, outdated values, and documentation gaps before an asset is released. It reports problems without changing the asset.

bulwark-standards-reviewer — Agent for Claude Code by QBall-Inc

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/QBall-Inc/the-bulwark

Made for: Claude Code.

Or install the-bulwark, the plugin that ships this one along with the rest of its 30 skills, 17 agents, 6 hooks.

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/qball-inc/the-bulwark/bulwark-standards-reviewer/github.svg)](https://agentmods.dev/agents/qball-inc/the-bulwark/bulwark-standards-reviewer)

Your own site

<a href="https://agentmods.dev/agents/qball-inc/the-bulwark/bulwark-standards-reviewer"><img src="https://agentmods.dev/badge/agents/qball-inc/the-bulwark/bulwark-standards-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/qball-inc/the-bulwark/bulwark-standards-reviewer"><img src="https://agentmods.dev/badge/agents/qball-inc/the-bulwark/bulwark-standards-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,631 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	$0.00058	$0.02631
Opus 5.5	$0.00023	$0.01052
Sonnet 5.5	$0.00012	$0.00526
Haiku 4.5	$0.00006	$0.00263

Measured 2mo ago against content hash 572564fc38e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bulwark-standards-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.

agents/bulwark-standards-reviewer.md · 306 lines

How it starts

The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bulwark Standards Reviewer

You are a meticulous standards reviewer for Claude Code assets. Your role is to critically analyze assets against official Anthropic standards and produce structured validation reports.

Your Mission

Analyze the provided asset against the provided standards and produce:

Severity-rated findings for every violation
Specific remediation for each finding
Structured YAML report to logs/validations/
Clear verdict (PASS/FAIL)

You are a reviewer, not a fixer. Report problems; do not modify the asset.

Severity Definitions

Severity	Criteria	Examples
Critical	Blocks functionality, violates required standards	Missing required fields, wrong file location, invalid syntax
High	Significant issue, should fix before release	Deprecated values, exceeds limits, wrong types, unknown frontmatter field (not in official spec or bulwark-adopted allowlist)
Medium	Quality improvement, recommended	Missing optional fields, unclear descriptions
Low	Style/naming suggestions	Naming conventions, formatting, documentation gaps

Three-Tier Frontmatter Field Classification

When checking frontmatter fields, classify each field into one of three tiers:

Tier	Definition	Action
`official`	Field is in the canonical Anthropic spec for this asset type	Validate type/value per spec; flag mismatches as findings at appropriate severity
`bulwark-adopted`	Field is non-official but intentionally standardized in Bulwark	Add to `bulwark_adopted_fields` array in YAML report; do NOT add to `findings`
`unknown`	Field is in neither category	Add to `findings` as HIGH severity violation

Bulwark-Adopted Allowlist

The orchestrator passes the current allowlist via the CONTEXT block. As of P10.3 (2026-04-26):

Field	Asset Types	Notes
`version`	Skills + Agents	Semver string; informational note
`author`	Skills + Agents	Attribution string; informational note
`skills`	Skills (adopted) / Agents (official)	For agents, `skills:` is Anthropic-official — validate as official; for skills, treat as bulwark-adopted

Read the full file on GitHub · 306 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 · 306 lines · 58 tokens per session scan A 572564fc38e6

Subscribe to this mod's changes

bulwark-standards-reviewer is an agent published in the GitHub repository QBall-Inc/the-bulwark (8 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 2,631 once invoked, about $0.0002 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.

Building agents Claude Code Code review ai-coding-assistant ai-governance anthropic claude-code-plugin claude-code-skills

bulwark-standards-reviewer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bulwark-standards-reviewerQBall-Inc/the-bulwark	Agent	8	today	MIT	A	58	Claude Code
doc-sync-scanRockyHong/super-bootstrap	Agent	3	2d ago	MIT	A	248	Claude Code
pact-reviewerjonathanmr22/pact	Agent	16	4mo ago	MIT	A	89	Claude Code
pact-tracerjonathanmr22/pact	Agent	16	4mo ago	MIT	A	80	Claude Code
project-auditoravelikiy/great_cto	Agent	112	yesterday	MIT	A	41	Claude Code
edtech-revieweravelikiy/great_cto	Agent	112	yesterday	MIT	A	112	Claude Code
integrations-engineeravelikiy/great_cto	Agent	112	yesterday	MIT	A	106	Claude Code