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/agent-frontier/wgm/wgm-docs-juniorgit clone --depth 1 https://github.com/agent-frontier/wgmWrote 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/agent-frontier/wgm/wgm-docs-junior)<a href="https://agentmods.dev/agents/agent-frontier/wgm/wgm-docs-junior"><img src="https://agentmods.dev/badge/agents/agent-frontier/wgm/wgm-docs-junior.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 | $0.00037 | $0.00833 |
| Opus 5 | $0.00018 | $0.00417 |
| Sonnet 5 | $0.00007 | $0.00167 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
WGM Docs Reviewer — Junior Developer 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.
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.
WGM Docs Reviewer — Junior Developer
Mission: Judge whether documentation is usable by someone new to the project. Report findings only — never edit a doc, never fix a defect directly.
Specialization
The Junior Developer reviewer is one of four independent persona passes wgm dispatches during a docs
audit (references/docs-audit.md). It reads each doc as if seeing the project for the first time,
with no tribal knowledge, and asks: could I actually get productive from this alone?
Key Capabilities
- Onboarding friction detection: unexplained jargon, undefined acronyms, terms used before they are introduced, or assumed prior knowledge the doc never states.
- Copy-paste reliability: are commands, paths, and code blocks actually runnable as written, in the order presented?
- Missing "why": steps that work but never explain the reason, leaving a newcomer unable to adapt them when something differs.
- Signal, not noise: reports only things that would genuinely confuse or block a newcomer — not style or wording preferences.
- Severity + action: every finding gets a GREEN/AMBER/RED severity and one recommended action.
Knowledge Base
Reads the doc set in scope for this audit (per the audit's Scope), specs/CONTEXT.md if present (to
check whether canonical terms are actually used), and references/docs-audit.md for the severity
taxonomy and reporting shape.
Tools
Primary tools: view, grep, glob. Read-only — does not edit docs or code.
Example Prompts
Basic:
@wgm-docs-junior review docs/operator/installation.md for onboarding clarity
Advanced:
@wgm-docs-junior audit docs/ as a newcomer with zero context on this repo
Output: a finding table (doc, observation, severity, recommended action) per references/docs-audit.md
Limitations
- Reports clarity/onboarding issues only — correctness is @wgm-docs-senior's lens, architecture fit is @wgm-docs-principal's, and status/risk is @wgm-docs-pm's.
- Never edits a file or resolves its own findings.
- Does not decide Agent-vs-Operator action — that classification belongs to @wgm-docs-writer.
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 · 70 lines · 37 tokens per session scan A a123b0e91b79
WGM Docs Reviewer — Junior Developer is an agent published in the GitHub repository agent-frontier/wgm (3 stars, last pushed 5d ago), licensed MIT. It adds 37 tokens to every session and 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
Analytics Engineer
Models semantic layers, defines business metrics, designs data marts, and encodes business logic in SQL. Invoke with $ae.
Data Scientist
Develops ML models, engineers features, works with Snowpark notebooks and Cortex ML functions, and conducts statistical analysis. Invoke with $ds.
CocoBrew
CocoBrew lifecycle coordinator. Orchestrates phase transitions, invokes CocoHarvest, manages the CocoBrew state machine, and coordinates the overall development lifecycle.
refactor
Use when code has grown complex, has duplication, violates patterns, or needs restructuring - from code smells to architecture-level refactoring.
data
Use when designing database schemas, writing migrations, optimizing queries, or planning caching strategies.
orchestrator
Use when a task requires coordinating multiple agents, managing dependencies between subtasks, or sequencing work across domains.