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/ramdhavepreetam/nervapack/querygit clone --depth 1 https://github.com/ramdhavepreetam/NervaPackWrote 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/ramdhavepreetam/nervapack/query)<a href="https://agentmods.dev/commands/ramdhavepreetam/nervapack/query"><img src="https://agentmods.dev/badge/commands/ramdhavepreetam/nervapack/query.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 | $0.00000 | $0.00680 |
| Opus 5 | $0.00000 | $0.00340 |
| Sonnet 5 | $0.00000 | $0.00136 |
| Haiku 4.5 | $0.00000 | $0.00068 |
Grade A, and why
query 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 3d 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.
nervapack query
Search the knowledge graph using natural language.
Synopsis
nervapack query "<prompt>"
Description
The query command retrieves focused, token-efficient context from the knowledge graph for a given prompt. It uses a query router that selects the best retrieval strategy automatically:
- Impact intent — if the prompt starts with
"what breaks if I change ..."or contains"impact of", triggers reverse dependency traversal to find callers and dependents. - Exact symbol match — if the prompt exactly matches a node name in the graph, seeds the BFS from that node directly, bypassing vector search.
- Semantic (vector) search — default fallback; embeds the prompt and finds the nearest nodes in ChromaDB, then expands with K-Hop BFS.
After retrieving a subgraph, query also injects any memory nodes that TOUCH the retrieved source files, so you see relevant past decisions alongside live code context.
Arguments
| Argument | Description |
|---|---|
PROMPT |
Natural language question or symbol name |
Examples
Standard semantic query
nervapack query "How does the token counting work?"
Exact symbol lookup
nervapack query "GraphRetriever"
Impact analysis
nervapack query "what breaks if I change VectorStore"
nervapack query "impact of GraphBuilder"
Output
Query Router: Intent: semantic, Direction: both
Vector Search: Found 3 seed nodes
┌─┬──────────┬──────────────────────────────┐
│#│ Node Type│ Name/File │
├─┼──────────┼──────────────────────────────┤
│1│ function │ count_tokens │
│2│ function │ render_savings_panel │
│3│ import │ tiktoken │
└─┴──────────┴──────────────────────────────┘
Graph Traversal: Expanding with max_hops=1, direction=both
📁 token_meter.py (2 entities)
⚙ count_tokens [seed]
⚙ render_savings_panel [seed]
← EXPLAINS: Token Efficiency
────────────────────────────────────────────────────────────
Retrieved Context (Markdown)
────────────────────────────────────────────────────────────
...
╭────────────── NervaPack Token Efficiency ──────────────╮
│ Naive RAG 12,340 ████████████ 100% (base) │
│ NervaPack 893 █░░░░░░░░░░░ 7.2% │
│ Tokens saved: 11,447 Reduction: 92.8% │
╰───────────────────────────────────────────────────────────╯
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.
- 3d ago First seen · 95 lines · 0 tokens per session scan A 14f5e5fab791
query is a command published in the GitHub repository ramdhavepreetam/NervaPack (1 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 680 tokens. 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
git
Git operations with intelligent commit messages and workflow optimization.
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.