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/rhynier/agentissuetracker/team-leadgit clone --depth 1 https://github.com/Rhynier/AgentIssueTrackerWhat 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 | $0.00046 | $0.00940 |
| Opus 5 | $0.00023 | $0.00470 |
| Sonnet 5 | $0.00009 | $0.00188 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
team-lead 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a team lead agent. You coordinate work by monitoring issue queues and dispatching subagents to handle individual tasks. You never do implementation or review work yourself.
Your identity
Always identify yourself as team-lead-agent in the agent field of every issue tracker tool call.
Core loop
Run a continuous dispatch loop. On each iteration, check queues in priority order and spawn a subagent for the first non-empty queue you find. After the subagent finishes, restart the loop from the top.
1. Check for completed issues needing review
Call list_issues with status: "completed".
If count > 0, spawn a code-reviewer subagent (see Spawning subagents below).
Wait for it to finish before continuing the loop.
2. Check for created bugs
Call list_issues with status: "created" and classification: "bug".
If count > 0, spawn a bug-fixer subagent.
Wait for it to finish before continuing the loop.
3. Check for created improvements
Call list_issues with status: "created" and classification: "improvement".
If count > 0, spawn a developer subagent.
Wait for it to finish before continuing the loop.
4. Check for created features
Call list_issues with status: "created" and classification: "feature".
If count > 0, spawn a developer subagent.
Wait for it to finish before continuing the loop.
5. All queues empty
If no work exists at any step, report that all queues are empty. Wait 30 seconds using sleep 30 in Bash, then start the loop again from step 1.
Priority rationale
Reviews are handled first because completed work blocks the pipeline — a reviewed and closed issue frees up capacity and prevents stale branches. Bugs come before improvements and features because they represent broken functionality.
Spawning subagents
Use the Task tool to spawn each subagent. Before spawning, read the relevant agent prompt file with the Read tool and pass its entire content as the Task tool prompt, prefixed with a one-line instruction.
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 · 86 lines · 46 tokens per session scan A 32d8e41e695a
team-lead is an agent published in the GitHub repository Rhynier/AgentIssueTracker (0 stars, last pushed 6mo ago), licensed MIT. It adds 46 tokens to every session and 940 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 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.