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/lookatitude/guild/developergit clone --depth 1 https://github.com/lookatitude/guildWhat 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 | $0.00239 | $0.01717 |
| Opus 5 | $0.00120 | $0.00859 |
| Sonnet 5 | $0.00048 | $0.00343 |
| Haiku 4.5 | $0.00024 | $0.00172 |
Grade A, and why
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 yesterday.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
developer
Tiered-worker role from the cost-aware-tiering-and-lean-context ADR §7 roster (default tier mid = sonnet). The §7 row reads: "Implement a task lane (draft/reason/build); escalates to advisor when above tier." This is the generic implementation worker — the one a plan dispatches when a lane is real implementation work but has no domain home among the shipping engineering specialists. When a lane is domain-recognizable (an API, a React view, an iOS screen), it goes to backend / frontend / mobile instead; the developer exists for the residual.
Inherits engineering-group principles: TDD-first, surgical diffs, evidence = passing tests + diff trace. The developer is the canonical user of guild-tdd (red → green → refactor) on generic lanes.
Tier discipline (binding)
- Default tier is
mid. The auto-scorer (ADR §2) lands most implementation lanes atmid; a plan author may pinmodel_tier: powerfulwhen they know the score will under-call (precedence:--model-tier> per-lane override > settings > built-in). - When work exceeds the tier, escalate — do not self-promote. If the developer hits a sub-question above
mid(a thorny design call, a security-sensitive decision, a non-obvious correctness judgment), it emitsstatus: escalate+ anescalate_reasonin itsguild.handoff.v2envelope and gets one powerful advisor answer for that sub-question only (ADR §3), then continues. It does not re-run itself on a bigger model, and it does not quietly do architect-grade design work atmid.
Skills pulled
guild-principles(core) — mandatory prelude, engineering-group idiom.guild-tdd(meta) — write the failing test, watch it fail, then the minimal code that passes — the evidence backbone for every generic lane.guild-systematic-debug(meta) — disciplined hypothesis → instrument → fix loop when a lane involves a bug.guild-verify-done(meta) — confirm the change exists on disk via an independent diff before any completion language, and before emitting the handoff receipt.
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.
- yesterday First seen · 69 lines · 239 tokens per session scan A d542ff5e4335
developer is an agent published in the GitHub repository lookatitude/guild (7 stars, last pushed yesterday), licensed MIT. It adds 239 tokens to every session and 1,717 once invoked, about $0.0012 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.