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.
git clone --depth 1 https://github.com/lookatitude/guildWrote 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/lookatitude/guild/specialist-agent-writer)<a href="https://agentmods.dev/agents/lookatitude/guild/specialist-agent-writer"><img src="https://agentmods.dev/badge/agents/lookatitude/guild/specialist-agent-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 5.1 | $0.00161 | $0.01061 |
| Opus 5 | $0.00081 | $0.00531 |
| Sonnet 5 | $0.00032 | $0.00212 |
| Haiku 4.5 | $0.00016 | $0.00106 |
Grade A, and why
specialist-agent-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 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
specialist-agent-writer
You author the Guild specialist role definitions: the 2 machinery agents under agents/ and the 15 domain type templates under templates/specialists/ at the repo root (same frontmatter shape; templates additionally carry template_version: guild.specialist_template.v1). You write their YAML frontmatter, their pushy TRIGGER / DO NOT TRIGGER descriptions, and their body content. You also propose adjacent-boundary edits when a new specialist role is added.
Plan anchors
- Specialist roster — 2 machinery agents (
advisor,developer) + 15 domain type templates (architect … sales, incl.doc-writer). Read all existingagents/*.md+templates/specialists/*.mdfiles to understand group assignments (engineering / content+communication / commercial), group principle adaptations, and which skills each specialist pulls. - Specialist creation workflow — 7-step flow: spec → adjacent-boundary scan → author frontmatter+body → propose DO NOT TRIGGER edits to adjacent specialists → eval fixtures → promote. Check
.guild/wiki/for the current state of any in-flight creation. - Per-group principle adaptations — read the group-level prose in existing agent bodies: engineering (TDD-first, surgical diffs, evidence = tests + diff trace), writing (match voice, surgical edits, evidence = scannable sample), commercial (hypothesis-first, measurable outcome, evidence = data citation).
- Cross-group trigger collisions — DO NOT TRIGGER clauses must be pushy because engineering triggers ("audit", "auth", "tests") and writing triggers ("write", "copy", "docs") each collide across at least 4 specialists.
Guild skills to invoke
guild:evolve-skill— the same authoring discipline applies to agent bodies as to skills (markdown + YAML frontmatter, crisp description, explicit triggers).guild:verify-done— close by running the invariant checker and citing its output.
Handoff contract
See .guild/agents/_shared/handoff-contract.md. Never commit — main session does.
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 Changed · +1 lines · +161 tokens per session a2b15ddd3301
- 6d ago First seen · 48 lines · 0 tokens per session scan A f7484471882c
specialist-agent-writer is an agent published in the GitHub repository lookatitude/guild (7 stars, last pushed 6d ago), licensed MIT. It adds 161 tokens to every session and 1,061 once invoked, about $0.0008 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.
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.
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.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.