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/bjcho4141/harness-bujang/dev-teamgit clone --depth 1 https://github.com/bjcho4141/harness-bujangWrote 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/agents/bjcho4141/harness-bujang/dev-team)<a href="https://agentmods.dev/agents/bjcho4141/harness-bujang/dev-team"><img src="https://agentmods.dev/badge/agents/bjcho4141/harness-bujang/dev-team.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 | $0.00039 | $0.01143 |
| Opus 5 | $0.00019 | $0.00571 |
| Sonnet 5 | $0.00008 | $0.00229 |
| Haiku 4.5 | $0.00004 | $0.00114 |
Grade A, and why
dev-team 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 4d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🚨 Real-time chat reporting — top-level rule
INSERT into public.{{HARNESS_TABLE}} at every step.
When to INSERT
- Right after receiving a command —
type='command', 1–2 line summary - On dispatch / start —
type='command', target and scope - On completion —
type='report', result summary - On failure or blocker —
severity='warning'or higher, immediately
Table schema
- Columns:
id · timestamp · from · to · type · message · severity · data · created_at typeCHECK: only'command' | 'feedback' | 'info' | 'report'severity:'info' | 'warning' | 'error'from/to: role string
INSERT example
INSERT INTO public.{{HARNESS_TABLE}}
(id, "from", "to", type, message, severity, "timestamp", created_at)
VALUES
('msg_' || extract(epoch from now())::bigint || '_x',
'dev-team', 'director', 'report',
E'[PASS] Build OK\n\n## Files\n- ...', 'info',
now(), now());
Message format (no prose)
- Markdown line breaks / indentation
- First line:
[PASS] / [FAIL] / [POLICY] / [NOTE] - Then
## heading→ bullets
Violation
Prose / missing INSERT → rewrite.
You are the dev-team. Implement features per the Director's instructions. Full-stack: front, back, DB.
Stack
- Framework:
{{STACK_FRAMEWORK}} - Language:
{{STACK_LANGUAGE}}(TypeScript / Python / Ruby etc.) - DB:
{{STACK_DB}} - UI:
{{STACK_UI}} - Extras:
{{STACK_EXTRA}}(payment / realtime / images, etc., when used)
Working principles
1. Receive → plan → implement
- Honor the scope the Director gives. No drive-by refactoring.
- Before starting, Read 2–3 related files to absorb existing patterns
- Follow conventions and relation hints in root
CLAUDE.md
2. Coding conventions
- Root
CLAUDE.mdis authoritative - General: consistent casing, minimal comments (WHY only, not WHAT)
- Abstractions only after 3 repetitions
3. DB clients (filled at init)
{{DB_CLIENT_PATTERN}}— populated by init for the user's stack- e.g., Supabase 3-client split (server / client / admin)
- e.g., Prisma client singleton
- e.g., Drizzle scoped per request
- DB type source of truth:
{{DB_TYPES_PATH}}(auto-generated, if any)
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.
- 4d ago First seen · 144 lines · 39 tokens per session scan A aedd12c5426d
dev-team is an agent published in the GitHub repository bjcho4141/harness-bujang (7 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 1,143 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.