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.
git 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/commands/bjcho4141/harness-bujang/bujang-team)<a href="https://agentmods.dev/commands/bjcho4141/harness-bujang/bujang-team"><img src="https://agentmods.dev/badge/commands/bjcho4141/harness-bujang/bujang-team/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/bjcho4141/harness-bujang/bujang-team"><img src="https://agentmods.dev/badge/commands/bjcho4141/harness-bujang/bujang-team.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00028 | $0.00775 |
| Opus 5 | $0.00014 | $0.00387 |
| Sonnet 5 | $0.00006 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
bujang-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 11d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/bujang-team
Direct shortcut to invoke one of the specialist teams without going through the full Director dispatch flow.
Usage
/bujang-team <team-name> <task>
Examples:
/bujang-team code-review-team review the latest commit
/bujang-team security-team audit the new payment endpoint
/bujang-team db-guard-team verify the migration in supabase/migrations/00031_*
/bujang-team qa-team run scenarios for the cart flow
Action — execute now
Parse <team-name> and <task> from the user's command arguments.
Step 1. Validate team name
The team name MUST be one of:
dev-team— actual code workarchitect-team— structure design / reviewdoc-sync-team— docs synccode-review-team— convention / readability reviewsecurity-team— auth / permissions / PII / XSS auditdb-guard-team— schema / FK / migration auditqa-team— functional / scenario verificationverifier-team— final build + regression gateconsultant— external benchmarking / industry advice
If invalid, print the list above and stop.
Step 2. Log the dispatch (chat-room write)
If the project has a chat-room DB configured, INSERT a row before invoking the agent. Use the project's existing pattern — look at lib/harness-db/ (if installed) or app/api/harness/reply/route.ts for the canonical write path.
SQLite (default):
sqlite3 .harness/chat.db <<'SQL'
INSERT INTO harness_messages (from_role, to_role, type, severity, body)
VALUES ('director', '<team-name>', 'command', 'info', '<task>');
SQL
Supabase: hit the project's own /api/harness/reply route (or INSERT via the service-role client).
If no chat DB is configured (agents-only install), skip this step.
Step 3. Invoke the agent
Use the Agent tool:
Agent({
subagent_type: "<team-name>",
description: "<2-4 word summary of the task>",
prompt: "<the user's task verbatim, plus any project context the agent needs>"
})
Step 4. Log the return
After the agent returns its report, INSERT a return-trip row:
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.
- 11d ago First seen · 97 lines · 28 tokens per session scan A 3bc37c3c1574
bujang-team is a command published in the GitHub repository bjcho4141/harness-bujang (7 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 775 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.