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 commands/robisson/build-like-amazon-agent-skills/buildgit clone --depth 1 https://github.com/robisson/build-like-amazon-agent-skillsWrote 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/commands/robisson/build-like-amazon-agent-skills/build)<a href="https://agentmods.dev/commands/robisson/build-like-amazon-agent-skills/build"><img src="https://agentmods.dev/badge/commands/robisson/build-like-amazon-agent-skills/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 | $0.00000 | $0.05669 |
| Opus 5 | $0.00000 | $0.02835 |
| Sonnet 5 | $0.00000 | $0.01134 |
| Haiku 4.5 | $0.00000 | $0.00567 |
Grade A, and why
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 5d 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 — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build — Execute Specs
Path resolution: All
skills/,agents/, andpatterns/paths in this command are relative to the plugin root directory. If not found in the working directory, resolve from the plugin installation path.
⛔ Default Execution Mode: Fully Autonomous Until the Feature Is Done
Unlike /design and /wb, /build runs without human gates by default. The approval gates happened before /build (during spec creation in /design). Once specs exist and are approved, /build executes everything end-to-end.
When the user invokes /build (with no other instruction), the agent MUST:
- Read all specs in
specs/and identify the execution order (hardest-first, established during/design). - Execute every spec in order, end-to-end, without pausing between specs and without asking permission to continue.
- Within each spec, execute all waves wave-by-wave per the dependency graph, without pausing between waves.
- Within each wave, dispatch all tasks in parallel as sub-agents, without pausing between tasks.
- After each spec, run the Post-Implementation Review automatically (see end of this file). If verdict is PASSED or PASSED WITH FIXES NEEDED, proceed to the next spec without asking. Only FAILED stops execution to surface to the user.
- Stop only when all specs in
specs/are in a terminal state (every task[x]or[!]). At that point, present a single end-of-build summary.
When to stop and ask the user (the only valid reasons)
The agent MAY only stop autonomous execution when one of these is true:
- Hard blocker: a sub-agent reports
[!]blocked and the blocker requires human input (missing credential, missing upstream service, ambiguous design that needs clarification, etc.). Mark the task[!]with reason and present. - Failed Post-Implementation Review: verdict is
FAILED(fundamentally wrong implementation, requirement entirely unimplemented, architectural gap). Presentimplementation-review.mdand wait for guidance. - Green-build gate fails and cannot self-recover: tests broken in a way that cannot be fixed with a follow-up task within scope.
- The user explicitly asked to pause/checkpoint (see override below).
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.
- 5d ago First seen · 334 lines · 0 tokens per session scan A cd868a0985fd
build is a command published in the GitHub repository robisson/build-like-amazon-agent-skills (14 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,669 tokens. 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 2026-08-30.
Other commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
upgrade
Upgrade the skillshare CLI binary and/or the built-in skillshare skill.
release
Git geçmişinden hedef kitleye uygun sürüm notları oluştur.
spec-forge
Use when generating software specifications — full chain (Idea→Decompose→Tech Design + Feature Specs) or individual documents.
wp-set-attributes
The WP SET ATTRIBUTES command allows you to set the value of any attribute in a range, element, document. This command gives you access to any kind of 4D Write Pro internal attribute: character, paragraph, document, table, or image.
verify
Perform a non-destructive post-implementation verification gate validating the implementation against spec.md, plan.md, tasks.md, and constitution.md.