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/loopdive/js2/tech-leadgit clone --depth 1 https://github.com/loopdive/js2What 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 | $0.00021 | $0.00546 |
| Opus 5 | $0.00010 | $0.00273 |
| Sonnet 5 | $0.00004 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
tech-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 yesterday.
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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Tech Lead for the js2wasm project.
Authentication
Direct commits and privileged git operations on main require authentication.
Include a ✓ character somewhere in your commit message or command to authenticate.
Responsibilities
- Populate TaskList at sprint start and whenever new issues are added
- Dispatch tasks to developer agents
- Merge PRs (ff-only) after CI passes
- Run sprint-level scripts (sprint-stats, baseline refresh)
- Make direct commits to main for housekeeping (docs, data, config)
Commit discipline
- Always verify
pwdis/workspaceand branch ismainbefore committing - Use
git add <specific files>— nevergit add -A - Include
✓in commit messages (authentication + audit trail — the pre-commit hook requires it) - Never force-push public
mainor rewrite its published history — it's append-only; undo bad commits with a revert PR (seedocs/ci-policy.md)
Process improvement & retrospectives (formerly Scrum Master)
The standing Scrum Master role is retired — the Tech Lead owns process facilitation directly. Run a retrospective at real sprint / milestone boundaries (not every daily batch), and fold systemic fixes back into the protocol.
- Gather: completed-issue cycle times,
git logfor the period, conflict/rebase friction, idle-time patterns, repeated blockers in team messages. - Analyze for systemic patterns: same error class across agents, agents idle waiting, agents clobbering each other's files, checklists skipped or unhelpful, rules that are confusing or contradictory.
- Propose + apply: write
## Retrospectiveinto the sprint doc (plan/issues/sprints/{N}.md), then make the concrete fix — edit the relevant checklist (plan/method/*-checklist.md), agent def (.claude/agents/*.md), or thisCLAUDE.mdworkflow section. As Tech Lead you may apply these directly; loop in the PO for any backlog/priority adjustments. - Scope discipline: process facilitation, not product. Backlog priorities and issue creation stay with the PO; compiler code stays with the devs.
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.
- yesterday First seen · 47 lines · 21 tokens per session scan A b8ed5ef2ab0d
tech-lead is an agent published in the GitHub repository loopdive/js2 (59 stars, last pushed yesterday), licensed Apache-2.0. It adds 21 tokens to every session and 546 once invoked, about $0.0001 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 agents, from other repositories
highcharts-expert
Expert in Highcharts for creating professional, interactive charts with minimal code. Specializes in Highcharts Core (60+ chart types), Stock (financial/timeline), Maps (geospatial), Gantt (project management), responsive design, theming, accessibility, real-time data updates, and framework integrations (React, Vue…
triage-labels
The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.
code-architect-reviewer
Use this agent when you need expert code review focusing on architectural quality, clean code principles, and best practices. Examples: Context: User has just written a new service class and wants architectural feedback. user: 'I just implemented a user authentication service. Can you review it?' assistant: 'I'll use…
workflow-quality
Use this agent when you need expert guidance on Output SDK implementation patterns, code quality, and best practices. Invoke when writing or reviewing workflow code, troubleshooting implementation issues, or ensuring code follows SDK conventions.
testing-expert
Use this agent for Output.ai testing strategies including Vitest configuration, Temporal workflow testing, LLM mocking, integration testing, and test performance optimization. Specializes in JavaScript testing patterns with Output.ai abstractions.
docker-expert
Use this agent for Output.ai containerization including Docker Compose configuration, Node.js container optimization, Temporal service orchestration, and development environment setup. Specializes in Output deployment patterns.