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 commands/datacore-one/datacore/searchgit clone --depth 1 https://github.com/datacore-one/datacoreWrote 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/datacore-one/datacore/search)<a href="https://agentmods.dev/commands/datacore-one/datacore/search"><img src="https://agentmods.dev/badge/commands/datacore-one/datacore/search.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 | $0.00022 | $0.01370 |
| Opus 5 | $0.00011 | $0.00685 |
| Sonnet 5 | $0.00004 | $0.00274 |
| Haiku 4.5 | $0.00002 | $0.00137 |
Grade A, and why
search 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 today.
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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search
Command Context
When to Reference DIP-0021
Always reference when:
- Running multi-source search queries
- Combining internal + external results
- Enforcing latency contracts
- Offering /research for deeper exploration
Key decisions this DIP informs:
- Source registry determines which sources to query
- Timeout enforcement (5 second max)
- Graceful degradation when external sources unavailable
- Synthesis format: internal-first, then external enrichment
When to Reference DIP-0004
Always reference when:
- Performing Datacortex semantic search
- Synthesizing answers from documents
- Offering zettel creation
- Checking embedding status
Quick Reference
| Question | Answer |
|---|---|
| Search engine (internal)? | datacortex search |
| Search engine (external)? | Perplexity via MCP (perplexity_search) |
| Source registry? | .datacore/registry/sources.yaml |
| Settings? | .datacore/settings.yaml (search.timeout_ms) |
| Timeout? | 5000ms (configurable) |
| Default internal results? | Top 5 |
| What DIPs govern this? | DIP-0021, DIP-0004 |
Agents This Command Invokes
| Agent | Purpose |
|---|---|
| (none) | Direct datacortex + MCP tool calls |
Integration Points
- DIP-0021 - Multi-source search architecture
- DIP-0004 - Datacortex retrieval
- Source Registry -
.datacore/registry/sources.yaml
Multi-source semantic search: local knowledge (Datacortex) + web intelligence (Perplexity).
Query: $ARGUMENTS
Reads (at startup)
.datacore/registry/sources.yaml— identify sources withlayerscontainingsearchand valid API keys.datacore/settings.yaml— readsearch.timeout_ms(default 5000)
Behavior
Step 1: Run Searches in Parallel
Internal (always):
datacortex search "$ARGUMENTS" --top 5
External (if available):
Check sources.yaml for sources with layers: [search] and valid API keys. For each available source within the latency budget (max_latency_ms < timeout_ms):
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.
- today First seen · 188 lines · 22 tokens per session scan A b2516cb97e19
search is a command published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 1,370 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 2026-09-03.
Other commands, from other repositories
prd-review
Review the active PRD with Codex and stream normalized findings to JSONL.
prd-archive
Archive the active PRD (blocked until every accepted finding has a receipt).
prd-map
Build a codebase map so PRDs are written with repo context, not blind.
prd-split
Split the approved PRD into one issue spec per manifest entry.
rca-check
Lint an RCA or premortem document against the canonical template.
prd-os-init
Initialize prd-os in this repo (writes .prd-os/config.json).