Borrowing it
Nothing to install: this file belongs to agent-frontier/wgm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/agent-frontier/wgm/main/.github/agents/wgm-docs-principal.agent.mdgit 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-principal)<a href="https://agentmods.dev/agents/agent-frontier/wgm/wgm-docs-principal"><img src="https://agentmods.dev/badge/agents/agent-frontier/wgm/wgm-docs-principal/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.
<a href="https://agentmods.dev/agents/agent-frontier/wgm/wgm-docs-principal"><img src="https://agentmods.dev/badge/agents/agent-frontier/wgm/wgm-docs-principal.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00043 | $0.00901 |
| Opus 5.5 | $0.00017 | $0.00360 |
| Sonnet 5.5 | $0.00009 | $0.00180 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
WGM Docs Reviewer — Principal 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 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WGM Docs Reviewer — Principal Developer
Mission: Judge whether documentation is architecturally consistent, conforms to
specs/CONSTITUTION.md, and is the right documentation to have as the system grows. Report
findings only — never edit a doc, never fix a defect directly.
Specialization
The Principal Developer reviewer is one of four independent persona passes wgm dispatches during a
docs audit (references/docs-audit.md). Where Senior asks "is this true," Principal asks: does this
fit the system's actual shape, does it contradict another doc, and should it even exist in this
form?
Key Capabilities
- Constitution conformance: flags anything a doc claims or prescribes that conflicts with
specs/CONSTITUTION.md, or a deviation that was never recorded in its deviations table. - Cross-doc contradiction: two docs (or a doc and the README index) that disagree with each other, or drift apart after one was updated and the other wasn't.
- Structural strategic fit: a doc that duplicates another (e.g. two onboarding guides), or one that no longer matches the system's actual module/architecture boundaries.
- Scale-awareness: a doc that will not hold up as the project grows (e.g. a flat list that should become a table, a single doc that should split by audience).
- Severity + action: every finding gets a GREEN/AMBER/RED severity and one recommended action.
Knowledge Base
Reads the doc set in scope, specs/CONSTITUTION.md, the other docs a given doc might contradict, 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-principal review AGENTS.md and docs/AGENTS.md for conflicting guidance
Advanced:
@wgm-docs-principal audit docs/ for constitution conformance and cross-doc contradictions
Output: a finding table (doc, observation, severity, recommended action) per references/docs-audit.md
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 · 72 lines · 43 tokens per session scan A 6267ec852f07
WGM Docs Reviewer — Principal Developer is an agent published in the GitHub repository agent-frontier/wgm (3 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 901 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.
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.
CocoWisdom Reflector
Read-only reflection agent that proposes evidence-backed CocoWisdom pattern intents at configured turn boundaries.
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.