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/martian56/claude-engineer/execute-buildnpx skills add martian56/claude-engineer --skill execute-buildgit clone --depth 1 https://github.com/martian56/claude-engineerWrote 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/martian56/claude-engineer/execute-build)<a href="https://agentmods.dev/skills/martian56/claude-engineer/execute-build"><img src="https://agentmods.dev/badge/skills/martian56/claude-engineer/execute-build.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 | $0.00047 | $0.00633 |
| Opus 5 | $0.00023 | $0.00316 |
| Sonnet 5 | $0.00009 | $0.00127 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
execute-build 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute Build
Announce at start: "I'm using claude-engineer:execute-build to drive the autonomous build."
Iron Law
Only run after the user signed off on the plan (claude-engineer:plan-project). If there is no
signed-off plan in docs/plan/, stop and go back.
The drive loop
- Read state first (
.claude-engineer/memory.md,progress.md,current-phase.txt). Trust them over recollection. - Isolate the workspace via
superpowers:using-git-worktreesbefore writing code. - Work phases in CX-first order (from the plan): Phase 0 scaffold → 1 design system → 2 frontend → 3 backend → 4 integration → 5 quality/CI/finish. Invoke the matching claude-engineer domain skill for each phase:
project-conventions,monorepo-and-tooling,docker-dev-environment(scaffold)design-system→frontend-development→backend-developmenttesting-and-quality,ci-cd-pipeline
- Execute tasks with
superpowers:subagent-driven-development- a fresh implementer subagent per task; each task usessuperpowers:test-driven-development. Usesuperpowers:dispatching-parallel-agentsfor independent workstreams. Fall back tosuperpowers:executing-plansonly where subagents are unavailable. - After each task: update
.claude-engineer/progress.md; record decisions inmemory.md. - When something breaks:
superpowers:systematic-debugging(root cause before fixes). - Review gate per phase / major feature:
superpowers:requesting-code-review+superpowers:receiving-code-review. - Before claiming any phase "done":
superpowers:verification-before-completionAND run the four gates viaclaude-engineer:testing-and-quality. - Finish:
claude-engineer:ci-cd-pipelinethensuperpowers:finishing-a-development-branch.
Autonomy & stopping
Plan-gated then autonomous: run to completion without check-ins. Stop only on genuine blockers - ambiguous requirements not covered by the brief, a destructive/irreversible action, missing credentials, or a decision that changes the agreed plan. Surface the blocker crisply with options.
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 · 38 lines · 47 tokens per session scan A 250c0b1a7de0
execute-build is a skill published in the GitHub repository martian56/claude-engineer (2 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 633 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 skills, from other repositories
adopt-project
Apply agent-starter patterns to an EXISTING project - audits the codebase, proposes components by invasiveness tier (hooks, skills, CLAUDE.md, lint configs, patterns), and applies only what the developer approves. Use when the user says adopt, retrofit, "apply agent-starter to this project", or wants starter patterns…
commit-push-pr
Full git workflow - creates branch, commits, pushes, and creates or updates a PR with summary and test plan.
commit
Create a single well-crafted git commit from current changes. Analyzes diff, follows repo's commit style, and writes a concise "why not what" message.
remember
Review auto-memory entries and propose promotions to CLAUDE.md, CLAUDE.local.md, or shared memory. Also detects outdated, conflicting, and duplicate entries across memory layers.
reflect
Per-project self-improvement - reads the .harness ledger and feedback memories, then proposes gated rule/threshold/ADR changes so the project stops repeating mistakes. Run periodically.
dream
Memory consolidation - review, merge, prune, and index memory files. Run periodically to keep memories organized and up-to-date.