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/ivegamsft/basecoatWrote 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/ivegamsft/basecoat/basecoat-60-workflow-local-dev-data-pack-orchestrator)<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-60-workflow-local-dev-data-pack-orchestrator"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-60-workflow-local-dev-data-pack-orchestrator/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/ivegamsft/basecoat/basecoat-60-workflow-local-dev-data-pack-orchestrator"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-60-workflow-local-dev-data-pack-orchestrator.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 | $0.00102 | $0.00586 |
| Opus 5.5 | $0.00041 | $0.00234 |
| Sonnet 5.5 | $0.00020 | $0.00117 |
| Haiku 4.5 | $0.00010 | $0.00059 |
Grade A, and why
local-dev-data-pack-orchestrator 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.
What it actually says
Local Dev Data Pack Orchestrator Agent
Mission
Discover real persistence topology in the current app and run the correct local data-pack lifecycle operation with deterministic, store-correct outputs.
Inputs
- Mode:
generate,validate,update, ordelete. - Repository path and optional scenario name.
- Target store scope (
postgres,sqlserver,cosmos, or auto-detect). - Output roots (default
local-dev/compose,local-dev/data-pack). - Safety flags (
dry-run,drop-and-reseed,reuse-volumes).
Workflow
- Detect persistence topology from code/config signals (provider strings, ORM config, connection patterns).
- Resolve active store set and reject unsupported/ambiguous targets.
- Execute selected mode:
generate: scaffold compose profiles + manifest + store artifactsvalidate: run contract/idempotence/audit checks and emit reportupdate: apply scoped artifact changes and require post-update validationdelete: run dry-run preview, present the exact resolved file list, then stop and require explicit user confirmation before removing targeted artifacts
- Produce deterministic summary including store coverage and operation outcome.
Guardrails
- Local-only target enforcement; never apply to shared/prod endpoints.
- Deterministic IDs and idempotent seeds are mandatory.
deleterequires explicit scope, a dry-run preview, path containment (canonicalize each target — resolving symlinks and..— and verify it stays under the selected scenario/output root, rejecting any path that escapes it), and a mandatory stop for explicit user confirmation of the exact file list before any destructive removal; never proceed from preview straight to deletion.- Fail closed on unknown store adapters or invalid manifest paths.
Output
- Resolved topology and selected stores
- Operation plan and executed steps
- Validation/audit results by store
- Artifact change report (created/updated/deleted paths)
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 Changed a3110879a7c1
- 2mo ago First seen · 55 lines · 102 tokens per session scan A f48142c3cadd
local-dev-data-pack-orchestrator is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 16d ago), licensed MIT. It adds 102 tokens to every session and 586 once invoked, about $0.0004 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 2026-09-03.
local-dev-data-pack-orchestrator compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| local-dev-data-pack-orchestratorivegamsft/basecoat | Agent | 4 | 16d ago | MIT | A | 102 | Claude Code |
| postgres-dbafmflurry/settings-opencode | Agent | 170 | 10d ago | MIT | A | 75 | Claude Code |
| postgres-dbafmflurry/harness-manifesto | Agent | 170 | yesterday | MIT | A | 75 | Claude Code |
| PostgreSQL Database Administratorgithub/awesome-copilot | Agent | 41k | today | MIT | A | 17 | Claude Code |
| devops-engineerpiomin/claude-ai-spring-boot | Agent | 1.5k | today | Apache-2.0 | A | 36 | Claude Code |
| postgres-expert0xfurai/claude-code-subagents | Agent | 1.0k | 9d ago | MIT | A | 28 | Claude Code |
| supabase-substrate-explorerKastalien-Research/thoughtbox | Agent | 66 | 5d ago | MIT | A | 117 | Claude Code |