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 skills add Guild-Agents/guild --skill build-featuregit clone --depth 1 https://github.com/Guild-Agents/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/skills/guild-agents/guild/build-feature)<a href="https://agentmods.dev/skills/guild-agents/guild/build-feature"><img src="https://agentmods.dev/badge/skills/guild-agents/guild/build-feature/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/skills/guild-agents/guild/build-feature"><img src="https://agentmods.dev/badge/skills/guild-agents/guild/build-feature.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 | $0.00015 | $0.04040 |
| Opus 5.5 | $0.00006 | $0.01616 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 3mo ago), licensed MIT. It adds 15 tokens to every session and 4,040 once invoked, about $0.0001 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 skills, from other repositories
code-review
Review local code changes. Uses an isolated sub-agent for unbiased analysis when the main agent wrote the code; reviews directly in fresh review-only sessions. Checks correctness, conventions, performance, tests, security, and tech design compliance. Use when the user wants a code review or says "review the diff" /…
security-review
Security-focused review rules for command and secret-sensitive changes.
atomic-review
Compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", or invokes /atomic-review. Auto-triggers when reviewing pull requests.
ralphctl-code-review-and-quality
Multi-phase code-quality skill — primary frame for the evaluator role in Execute, the architecture axis in Plan, and correctness/readability in Refine. Multi-axis code review with severity vocabulary. Use when acting as the evaluator assessing a generator's output, and when reviewing any change before signalling…
code-review-helper
A safe skill that helps with code review tasks.
ensemble-beads-build
Drive an existing bead hierarchy to completion through the full builder, code-review, and close pipeline (Codex skill for /ensemble:beads-build).