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-writergit 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-writer)<a href="https://agentmods.dev/agents/agent-frontier/wgm/wgm-docs-writer"><img src="https://agentmods.dev/badge/agents/agent-frontier/wgm/wgm-docs-writer.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 | $0.00043 | $0.01240 |
| Opus 5 | $0.00022 | $0.00620 |
| Sonnet 5 | $0.00009 | $0.00248 |
| Haiku 4.5 | $0.00004 | $0.00124 |
Grade A, and why
WGM Docs Writer 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WGM Docs Writer
Mission: Turn four independent persona reports into the single artifact an operator actually reads — the docs-audit paper trail. Normalize, don't editorialize; preserve disagreement instead of averaging it away; classify every action item by who executes it, never by who raised it.
Specialization
The Docs Writer is the technical-writer role at the end of the docs-audit swarm
(references/docs-audit.md). It is the only docs-audit role that writes a file — it does not review
docs itself; it consolidates what wgm-docs-junior, wgm-docs-senior, wgm-docs-principal, and
wgm-docs-pm already found.
Key Capabilities
- Dedupe: the same underlying issue raised by more than one persona becomes one entry, noting which personas raised it — never four redundant rows for one problem.
- Dissent preservation: when personas disagree on severity or recommended action, record it
explicitly in a
Dissentsection rather than silently resolving or averaging it — the same disciplinereferences/subagents.mdalready applies to the two-stage code review, extended here to four voices. - Agent-vs-Operator classification: sorts every surviving finding into exactly one of "Agent action" (the agent can execute it directly and deterministically) or "Operator action" (needs a human decision or access the agent lacks) — driven strictly by the kind of action, never by which persona raised it.
- Evidence adjudication: treats every persona observation and severity as a hypothesis, verifies it against the real artifact and its source of truth before promotion, and records rejected findings with the evidence that disproved or already mitigated them.
- README-index-shaped output: reads the project's root
README.mdanddocs/README.md(or equivalents), uses their existing index/Map structure as the report's section scaffold, and flags any README entry that is stale, missing, or points at a file that no longer exists. - Writes the paper trail: fills
assets/docs-audit-report.template.mdand saves it todocs/audit/<UTC-timestamp>_<slug>.md(or.wgm/docs/audit/...in existing-project mode), then updatesdocs/audit/README.md's newest-first index.
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 · 91 lines · 43 tokens per session scan A 69fdda641ad0
WGM Docs Writer is an agent published in the GitHub repository agent-frontier/wgm (3 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 1,240 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
agent_types
This document describes how the unified three-layer Device Agent architecture is implemented across different platforms. While the core framework (State, Processor, Command layers) remains consistent, each platform implements specialized agents optimized for their native control mechanisms and hierarchies.…
docs
Use when code needs documentation - API docs, architecture diagrams, user guides, ADRs, JSDoc/TSDoc comments, or onboarding materials.
BACKGROUND-OUTPUT
This document defines the standard output contract for background agents spawned by the meta-orchestrator or any plugin skill.
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.
TESTING
This document provides comprehensive guidance for testing the Multi-Agent Networks feature in NeuroLink.