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 skills/guild-agents/guild/build-featurenpx skills add Guild-Agents/guild --skill build-featuregit clone --depth 1 https://github.com/Guild-Agents/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 | $0.00015 | $0.04040 |
| Opus 5 | $0.00008 | $0.02020 |
| Sonnet 5 | $0.00003 | $0.00808 |
| Haiku 4.5 | $0.00002 | $0.00404 |
Grade A, and why
build-feature 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 2d 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 — 449 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Feature
Full pipeline to build a feature end-to-end with all team agents. Each phase invokes a specialized agent using the Task tool.
When to use
- ANY code change with acceptance criteria or a spec — regardless of perceived size
- New features, enhancements, bug fixes with defined requirements
- Even "small" changes: if the user described what it should do, it goes through the pipeline
When NOT to use
- Typo fixes, config tweaks, dependency bumps — changes with no behavioral spec
- CLAUDE.md updates
- When the user explicitly says "do this without guild" or "just do it"
Usage
/build-feature [feature description]
Parallel Execution: Worktree Isolation
When multiple build-feature pipelines run in parallel, each MUST use its own git worktree to avoid branch conflicts:
git worktree add .claude/worktrees/[branch-name] -b [branch-name] develop
All file operations within the pipeline must use the worktree directory as the working directory. After the PR is merged, clean up with:
git worktree remove .claude/worktrees/[branch-name]
When running a single build-feature, a simple git checkout -b is sufficient.
5-Phase Pipeline
Progress Display
At the start of each phase, display a progress indicator to the user before any agent output:
[1/5] Advisor (opus) — Evaluating feature...
[2/5] Tech Lead (opus) — Defining spec and technical approach...
[3/5] Developer (sonnet) — Implementing...
[4/5] Code Reviewer (opus) — Reviewing changes...
[5/5] QA (sonnet) — Validating acceptance criteria...
When the preferred model for a tier is unavailable, show the fallback with an arrow indicating what was attempted:
[1/5] Advisor (sonnet ← opus) — Evaluating feature...
[3/5] Developer (haiku ← sonnet) — Implementing...
Display the normal format (just the model name) when the preferred model resolves successfully. Display the fallback format (actual ← preferred) only when a fallback was required.
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.
- 2d ago First seen · 449 lines · 15 tokens per session scan A 458a92ea1cc2
build-feature is a skill published in the GitHub repository Guild-Agents/guild (4 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 4,040 once invoked, about $0.0001 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 skills, from other repositories
codebase-memory
Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions…
using-pi-subagents
Operate pi-subagents jobs safely, including direct-work decisions, least-privilege tool selection, thinking-level selection, delegation, bidirectional messaging, parallel starts, timeout selection, waiting, cancellation, result handling, verification, and writer isolation.
herdr
Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another agent. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires…
debugging-output-and-previewing-html-using-ray
Use when user says "send to Ray," "show in Ray," "debug in Ray," "log to Ray," "display in Ray," or wants to visualize data, debug output, or show diagrams in the Ray desktop application.
fortify-development
ACTIVATE when the user works on authentication in Laravel. This includes login, registration, password reset, email verification, two-factor authentication (2FA/TOTP/QR codes/recovery codes), passkeys, profile updates, password confirmation, or any auth-related routes and controllers. Activate when the user mentions…
Shade dropdown surface contract
DropdownMenu, Select, and Popover share one visual recipe (bg-surface-elevated-2 + border-border/60 dark:border-border/30 + shadow-md). Change them together. Trigger when editing any of those three Shade files.