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 Maxmedawar/tandem --skill tandem-engineering-workflowgit clone --depth 1 https://github.com/Maxmedawar/tandemWrote 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/maxmedawar/tandem/tandem-engineering-workflow)<a href="https://agentmods.dev/skills/maxmedawar/tandem/tandem-engineering-workflow"><img src="https://agentmods.dev/badge/skills/maxmedawar/tandem/tandem-engineering-workflow.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 5.1 | $0.00067 | $0.00786 |
| Opus 5 | $0.00034 | $0.00393 |
| Sonnet 5 | $0.00013 | $0.00157 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade A, and why
tandem-engineering-workflow 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 7d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tandem engineering workflow
📋📋📋📋📋 The engineering workflow is active.
This skill defines how an MCP-capable director should plan, delegate, verify, and report engineering work performed through Tandem. It is engine-neutral. Engine-specific features, such as Claude model controls or the Claude-only relay, are optional special cases.
Roles
- Human: sets the goal, grants authority, makes consequential product decisions.
- Director: clarifies the outcome, selects devices and engines, assigns bounded work, and owns the final answer.
- Worker session: implements or investigates one defined part of the goal.
- Reviewer session: independently checks the result when the risk or scope warrants it.
One session may hold several roles on a small task. Keep ownership explicit on larger work.
Workflow
Understand
- Restate the concrete outcome and definition of done.
- Inspect the repository, current branch, local instructions, and existing changes before editing.
- Identify what is unknown and research only what affects the decision.
- Push back on unsafe, contradictory, or needlessly broad requests with concrete reasons.
Plan
- Break work into phases with clear file ownership and tests.
- Decide which assignments are independent and which depend on earlier output.
- Select a device and engine based on advertised capability and data locality. Do not route by guesswork.
- Use a planning mode when the chosen engine provides one and the work is non-trivial. Otherwise ask the worker for a written plan before implementation.
- Review the plan before authorizing broad writes. Correct scope drift before code is changed.
Build
- Give each worker a bounded assignment, the relevant context, and a measurable completion condition.
- Preserve user changes and avoid unrelated refactors.
- Keep security controls explicit: narrow cwd allowlists, opt-in engines, no secret output, and no permission bypass unless authorized.
- Poll a running turn instead of resending its prompt.
- Read the worker's actual result. A completion claim is not verification.
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.
- 7d ago First seen · 79 lines · 67 tokens per session scan A fd954eaa5cb9
tandem-engineering-workflow is a skill published in the GitHub repository Maxmedawar/tandem (25 stars, last pushed 25d ago), licensed MIT. It adds 67 tokens to every session and 786 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
adk-unit-design
Writes an as-built architecture document for one ADK code unit — purpose, execution flow, data flow, cross-class dependencies, extension points, and the parts that must not change — to docs/design/{topic}/{unit}/index.md. It describes the code as implemented, not a proposed design, and its reader is a developer about…
artifact-deploy
One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".
explain-for
Explain a topic, a piece of code, an error, or a design decision calibrated to one named audience — a 5-year-old, a 5th grader, a manager, a designer, a graduate student, a parent. Resolves who the explanation is for (from the request, or from what memory already records about that person), establishes the ground…
web-verify
Look at your OWN front-end change before claiming it works -- navigate the loopback URL of a dev server or pod you started, screenshot the surface you changed, read the image to judge it, and embed it in chat. Three capture backends: playwright-cli (the session the dashboard Browser panel shows), the agent-browser CLI…
learn-from-sage
Detection-gap (miss) analysis for Code Review Sage. Learn from shipped fixes, acted-on human comments, and design outcomes to close reviewer blind spots. Inline during review stages a candidate; a human triggers a one-shot AI consolidation into the live ruleset.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.