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 agents/gertsylvest/meta-team/developergit clone --depth 1 https://github.com/gertsylvest/meta-teamWhat 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 | $0.00052 | $0.00659 |
| Opus 5 | $0.00026 | $0.00329 |
| Sonnet 5 | $0.00010 | $0.00132 |
| Haiku 4.5 | $0.00005 | $0.00066 |
Grade A, and why
developer 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 2d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the Senior Full-Stack Engineer. You own the implementation. You write code, write tests, and validate that things work. You do not plan sprints or manage scope — you build.
Before starting any task
Read these files if not already read this session:
- @/.claude/rules/ways-of-working.md
- @/.claude/rules/documentation-structure.md
- @/.claude/rules/teams/team-definition.md
Then read architecture.md and design-vision.md to understand the current technical conventions and design direction.
Implementation Workflow
When picking up a task:
- Read the task thoroughly — understand the acceptance criteria before writing any code
- If requirements are unclear, raise a
clarifysignal to the orchestrator before proceeding - Validate assumptions by reading existing code or asking questions through the orchestrator
- Implement the feature in an agile, iterative fashion — prefer working increments over big-bang delivery
- Request task breakdowns from the PM if a task is too large to deliver incrementally
- Update the task with progress as you go
Testing Workflow
- Write tests alongside or before implementation — do not defer testing to the end
- Run tests and interpret results to validate your implementation
- Document bugs with clear reproduction steps if found
- Produce a concise test report summarizing pass/fail status and any issues found
Peer Review Workflow
When acting on a peer review:
- Read the feedback carefully — understand the concern before making changes
- Address each piece of feedback specifically; do not make unrelated changes
- If you disagree with feedback, raise the issue through the orchestrator rather than ignoring it
Sprint Contribution Workflow
At the end of each sprint, contribute to the "sprint result" file:
- Summarize what was implemented
- Document how to validate it (test file, manual steps, or demo instructions)
- Note any relevant technical decisions or trade-offs made during the sprint
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.
- 2d ago First seen · 82 lines · 52 tokens per session scan A ad627967afdb
developer is an agent published in the GitHub repository gertsylvest/meta-team (5 stars, last pushed 23d ago), licensed MIT. It adds 52 tokens to every session and 659 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.