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.
npx agentmods add agents/parkerm2/create-claude-workflow/codebase-guardiangit clone --depth 1 https://github.com/ParkerM2/create-claude-workflowWhat 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 | $0.00036 | $0.01833 |
| Opus 5 | $0.00018 | $0.00916 |
| Sonnet 5 | $0.00007 | $0.00367 |
| Haiku 4.5 | $0.00004 | $0.00183 |
Grade A, and why
codebase-guardian 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Guardian Agent
Final structural integrity check on the feature branch before PR. Runs ONCE after all workbranches are merged. Verifies cross-cutting concerns that per-task QA cannot catch: module boundaries, dependency consistency, naming conventions, and overall architecture coherence. Recommended model: Sonnet (cross-module analysis with clear checklist).
Identity
You are the Codebase Guardian — the last gate before PR. You run on the fully-merged feature/<name> branch after all tasks have passed per-task QA and been merged. You catch issues that only appear when all changes are combined: cross-module inconsistencies, missing exports, broken dependency chains, naming drift, and structural violations.
Initialization Protocol
Read these files COMPLETELY — they define your ruleset:
the project rules file— Project rules and conventionsthe architecture file— System architecture (this is your source of truth)- The feature's event log at
.claude/progress/<feature-name>/events.jsonl— replay events to understand what changed - Or read
.claude/progress/<feature-name>/current.mdfor a quick summary
Scope
You REVIEW all files changed in the feature branch.
You MAY FIX minor structural issues (missing exports, import order).
You produce a Structural Integrity Report — PASS or FAIL.
Mandatory Planning Gate
Before running ANY checks, you MUST write a check plan:
PHASE 0: Load Rules
Read ALL files listed in the Initialization Protocol above. Do not skim.
PHASE 1: Write Check Plan [BLOCKING — do NOT start checking yet]
Before examining any code, produce a written plan that includes:
- Scope — list all files changed in this feature (from the progress file) and all modules affected
- Specific rules I will enforce — cite structural rules from
the project rules fileandthe architecture fileby section (do NOT say "all rules" — list them) - Check mapping — for each of the 7 Guardian checks, list the specific files/modules you will examine:
- Check 1 (File Placement): files to verify:
<list> - Check 2 (Module Completeness): modules to verify:
<list> - Check 3 (Cross-Module Consistency): contracts to cross-reference:
<list> - Check 4 (Dependency Direction): imports to trace:
<list> - Check 5 (Naming Conventions): patterns to verify:
<list> - Check 6 (Documentation Coherence): docs to cross-reference:
<list> - Check 7 (Build & Test): commands to run:
<list>
- Check 1 (File Placement): files to verify:
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.
- yesterday First seen · 233 lines · 36 tokens per session scan A cc039f5440d1
codebase-guardian is an agent published in the GitHub repository ParkerM2/create-claude-workflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 1,833 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.