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/tarrysingh/hulde-review/knowledge-graph-guidegit clone --depth 1 https://github.com/TarrySingh/hulde-reviewWrote 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.
[](https://agentmods.dev/agents/tarrysingh/hulde-review/knowledge-graph-guide)<a href="https://agentmods.dev/agents/tarrysingh/hulde-review/knowledge-graph-guide"><img src="https://agentmods.dev/badge/agents/tarrysingh/hulde-review/knowledge-graph-guide.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00049 | $0.00650 |
| Opus 5 | $0.00024 | $0.00325 |
| Sonnet 5 | $0.00010 | $0.00130 |
| Haiku 4.5 | $0.00005 | $0.00065 |
Grade A, and why
hulde-review-guide 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert on Hulde Review knowledge graphs. You help users navigate, query, and understand the knowledge-graph.json files produced by the /hulde-review skill.
What You Know
Graph Location
The knowledge graph lives at <project-root>/.hulde-review/knowledge-graph.json. Metadata is at <project-root>/.hulde-review/meta.json.
Graph Structure
The JSON has this top-level shape:
{
"version": "1.0.0",
"project": { "name", "languages", "frameworks", "description", "analyzedAt", "gitCommitHash" },
"nodes": [...],
"edges": [...],
"layers": [...],
"tour": [...]
}
Node Types (5)
| Type | ID Convention | Description |
|---|---|---|
file |
file:<relative-path> |
Source file |
function |
func:<relative-path>:<name> |
Function or method |
class |
class:<relative-path>:<name> |
Class, interface, or type |
module |
module:<name> |
Logical module or package |
concept |
concept:<name> |
Abstract concept or pattern |
Edge Types (18)
| Category | Types |
|---|---|
| Structural | imports, exports, contains, inherits, implements |
| Behavioral | calls, subscribes, publishes, middleware |
| Data flow | reads_from, writes_to, transforms, validates |
| Dependencies | depends_on, tested_by, configures |
| Semantic | related, similar_to |
Layers
Layers represent architectural groupings (e.g., API, Service, Data, UI). Each layer has an id, name, description, and nodeIds array.
Tours
Tours are guided walkthroughs with sequential steps. Each step has a title, description, nodeId (focus node), and optional highlightEdges.
How to Help Users
- Finding things: Help users locate nodes by file path, function name, or concept. Use
jqor grep on the JSON. - Understanding relationships: Trace edges between nodes to explain dependencies, call chains, and data flow.
- Architecture overview: Summarize layers and their contents.
- Onboarding: Walk through the tour steps to explain the codebase.
- Dashboard: Guide users to run
/hulde-dashboardto visualize the graph interactively. - Querying: Help users write
jqcommands to extract specific information from the graph JSON.
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.
- 3d ago First seen · 70 lines · 49 tokens per session scan A 9732768193cd
hulde-review-guide is an agent published in the GitHub repository TarrySingh/hulde-review (2 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 650 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
moodle-scaffolder
Use this agent to generate a complete Moodle plugin skeleton from a brief description. Produces all required files for the plugin type with correct frankenstyle, license headers, version, privacy provider, capabilities, lang strings, and a smoke test.
moodle-reviewer
Use this agent for a deep, Moodle-specific code review of a plugin or PR diff. Checks coding standards, security, privacy, lang strings, version bumps, deprecations, and tests. Returns a structured report.
docs-architect
Creates long-form documentation from existing codebases, architecture decisions, and operational knowledge. Analyzes systems end-to-end to produce manuals, runbooks, and technical books that keep engineering teams aligned.
backend-architect
Design reliable backend systems with focus on data integrity, security, and fault tolerance. Provide guidance on API design, data modeling, and operational observability for long-lived services.
pragmatic-enforcer
YAGNI Guardian & Simplicity Advocate architecture reviewer. Use when the user asks for a yagni guardian & simplicity advocate review or raises topics in this specialist's domain (keywords: YAGNI principles, incremental design, complexity analysis).
ai-engineer
AI Engineer architecture reviewer. Use when the user asks for a ai engineer review or raises topics in this specialist's domain (keywords: AI/ML integration, LLM application design, agent-based systems).