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 tinhtran24/maestro --skill dev-lifecyclegit clone --depth 1 https://github.com/tinhtran24/maestroWrote 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/tinhtran24/maestro/dev-lifecycle)<a href="https://agentmods.dev/skills/tinhtran24/maestro/dev-lifecycle"><img src="https://agentmods.dev/badge/skills/tinhtran24/maestro/dev-lifecycle/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/tinhtran24/maestro/dev-lifecycle"><img src="https://agentmods.dev/badge/skills/tinhtran24/maestro/dev-lifecycle.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 | $0.00054 | $0.00782 |
| Opus 5.5 | $0.00022 | $0.00313 |
| Sonnet 5.5 | $0.00011 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
dev-lifecycle 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development lifecycle
This is the delivery method every Maestro task follows. It distills a full software lifecycle (Define → Plan → Build → Verify → Review → Ship) into the two moments Maestro cares about: creating a task (Analysis + Plan) and doing the task (Development + Testing, then branch + commit). Method credit: addyosmani/agent-skills.
When a task is created: Analysis, then Plan
Do these in order and write them down in the task draft.
- Analysis — understand before proposing. Capture:
- the problem and the user story ("As a … I want … so that …");
- explicit acceptance criteria (observable, testable statements);
- scope (XS/S/M/L/XL) and the risks, dependencies, and open questions;
- the likely files/areas the change touches. Surface missing information instead of guessing it.
- Plan — decompose the analysis into small, verifiable steps ordered by dependency. Each step should be independently checkable. Prefer thin vertical slices over broad horizontal refactors.
A good task draft answers "what does done look like?" (acceptance criteria) and "what is the smallest sequence of verifiable steps to get there?" (plan) before any code is written.
When a task is executed: Development, then Testing
The orchestrator coordinates workers through these phases and surfaces each step so the human can see progress.
- Development — implement one plan step at a time as a thin slice. Keep changes surgical and tied to the task; avoid drive-by refactors.
- Testing — verify each slice: add or update tests at the boundary being changed, run the project's relevant checks, and exercise the real behavior (not just types/compile). Do not report a step complete while its checks fail.
Only after Development and Testing pass do you commit and open the pull request.
Branch naming and commits
Create the branch before the first commit. Use a prefix that matches the task's nature, then a short kebab-case description:
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 · 73 lines · 54 tokens per session scan A 7f97b68ed2cf
dev-lifecycle is a skill published in the GitHub repository tinhtran24/maestro (6 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 782 once invoked, about $0.0002 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
git-commit
Generate well-formatted git commit messages following conventional commit standards.
engineer-bot-getting-started
An onboarding guide for an engineering delivery assistant. It helps define a repository, the allowed level of access, and the work needed before reviewing a code change.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
security-pipeline
Use when security verification is needed - pre-commit security checks, vulnerability scanning, STRIDE threat analysis. Integrates with /handoff-verify --security and /commit-push-pr. CWE Top 25 based.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.
commit
Generate a conventional commit message for staged changes.