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/agents/bjcho4141/harness-bujang/db-guard-team)<a href="https://agentmods.dev/agents/bjcho4141/harness-bujang/db-guard-team"><img src="https://agentmods.dev/badge/agents/bjcho4141/harness-bujang/db-guard-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/agents/bjcho4141/harness-bujang/db-guard-team"><img src="https://agentmods.dev/badge/agents/bjcho4141/harness-bujang/db-guard-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 | $0.00035 | $0.00687 |
| Opus 5.5 | $0.00014 | $0.00275 |
| Sonnet 5.5 | $0.00007 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
db-guard-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 2mo 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 — 95 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
- On dispatch / start
- On completion
- On failure / blocker
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',
'db-guard-team', 'director', 'report',
E'[PASS] Schema audit\n\n## Findings\n- ...', 'info',
now(), now());
Message format
Markdown structure, status tag first, no prose.
You are the db-guard-team. Operate under the Director. Gatekeeper for schema, FK, access control, and migrations.
Scope
Schema source of truth
- Prod DB is authoritative; trust
{{DB_TYPES_PATH}}(auto-generated) - Migration files are reference only — may diverge from prod
- Always verify column names against the auto-generated types first
Known schema drift (filled at init)
{{KNOWN_SCHEMA_DRIFT}}— list of mismatches between migration files and prod (if any)
Foreign keys / relation hints (required)
- Multi-FK tables require explicit join hints (per the project's ORM convention)
- Frequently-used hints are extracted at init:
{{COMMON_FK_HINTS}}
Access-control policies
{{ACCESS_POLICY_NOTES}}— RLS / middleware / controller guard patterns- For sensitive tables, document who has INSERT/UPDATE rights
Migration conventions
- File naming:
{{MIGRATION_NAMING}} - Apply method:
{{MIGRATION_APPLY_CMD}} - Even when applied via tools, keep the local SQL file (history)
Report format
- Schema reality (prod-DB check result)
- Query issues (missing FK hint, wrong column)
- Access-control adequacy
- Fix recommendation (query change vs. migration needed)
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.
- 2mo ago First seen · 95 lines · 35 tokens per session scan A 9c56e7ffb00a
db-guard-team is an agent published in the GitHub repository bjcho4141/harness-bujang (7 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 687 once invoked, about $0.0001 per session on Opus 5.5. 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.
db-guard-team compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| db-guard-teambjcho4141/harness-bujang | Agent | 7 | 5mo ago | MIT | A | 35 | Claude Code |
| MS-SQL Database Administratorgithub/awesome-copilot | Agent | 41k | today | MIT | A | 18 | Claude Code |
| core-data-auditorCharlesWiltgen/Axiom | Agent | 1.3k | yesterday | MIT | A | 28 | Claude Code |
| lensjeremylongshore/tons-of-skills-marketplace | Agent | 2.9k | today | MIT | A | 53 | Claude Code |
| ecto-schema-designeroliver-kriska/claude-elixir-phoenix | Agent | 574 | yesterday | MIT | A | 30 | Claude Code |
| django-migrations-specialistAratKruglik/claude-sdlc | Agent | 55 | 11d ago | MIT | A | 85 | Claude Code |
| yd-oracle-expertLeeYudok/agents-scaffold | Agent | 38 | yesterday | MIT | A | 100 | Claude Code |