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 instructions/duhman/volterra-knowledge-engine/agents-mdgit clone --depth 1 https://github.com/duhman/volterra-knowledge-engineWrote 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/instructions/duhman/volterra-knowledge-engine/agents-md)<a href="https://agentmods.dev/instructions/duhman/volterra-knowledge-engine/agents-md"><img src="https://agentmods.dev/badge/instructions/duhman/volterra-knowledge-engine/agents-md.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 | $0.00659 | $0.00659 |
| Opus 5 | $0.00329 | $0.00329 |
| Sonnet 5 | $0.00132 | $0.00132 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
volterra-knowledge-engine AGENTS.md 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 2d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
src/holds the TypeScript source. Key areas:core/(pipeline orchestration),parsers/(file format extraction),sources/(Notion/SharePoint/HubSpot/Slack/file),services/(n8n client),compliance/(PII/GDPR),database/(Supabase client + migrations),scripts/(CLI entry points), andtypes/.supabase/migrations/contains timestamped SQL migrations that must be applied in order.supabase/functions/contains Edge Functions for daily syncs (Notion, Slack, HubSpot).config/default.jsonis the non-secret runtime configuration.docs/houses operational documentation.- Claude skills live in
.claude/skills/(e.g.volterra-kb/,n8n/).
Build, Test, and Development Commands
npm run devrunstsx watchfor local development.npm run buildcompiles TypeScript todist/;npm run startrunsdist/index.js.npm run typecheckrunstsc --noEmitfor static checks.- Ingestion entry points live in
src/scripts/(e.g.,npm run ingest:file,npm run ingest:notion,npm run ingest:slack -- --export-path /path). npm run n8nmanages n8n workflows (list/get/update/etc.), incltest+patch-supabase.npm run test:slack-envvalidates Slack Edge Function configuration.
Coding Style & Naming Conventions
- TypeScript ESM (
"type": "module"), strict mode; import paths include.jsextensions. - Indentation is 2 spaces; prefer small, focused modules.
- Naming:
PascalCasefor classes,camelCasefor functions/vars,kebab-casefor filenames (e.g.,batch-ingest.ts). - No formatter/linter is configured; keep style consistent with nearby files.
Testing Guidelines
- There is no dedicated test framework or
tests/directory. - Validate changes with
npm run typecheckand by running the relevant CLI script(s) for the area you touched (ingestion, sync, or training tools).
Commit & Pull Request Guidelines
- Recent commit messages are sentence-case, descriptive summaries (e.g., “Add Notion integration features…”). Follow that pattern.
- PRs should include: a brief summary, any new/updated env vars, migration files (if schema changes), and the exact commands used to validate changes.
- If adding migrations, note they must be run manually in Supabase SQL Editor and consider updating
src/types/database.types.ts.
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.
- 2d ago First seen · 42 lines · 659 tokens per session scan A 66c0ffcbd9da
volterra-knowledge-engine AGENTS.md is an instructions file published in the GitHub repository duhman/volterra-knowledge-engine (0 stars, last pushed 6mo ago), licensed MIT. It adds 659 tokens to every session, about $0.0033 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 instructions, from other repositories
markdown-vault-mcp AGENTS.md
Instructions for pvliesdonk/markdown-vault-mcp, covering markdown vault mcp, design, project structure, conventions and skills.
markdown-vault-mcp CLAUDE.md
Instructions for pvliesdonk/markdown-vault-mcp, a project described as: Generic markdown collection MCP server with FTS5 + semantic search, frontmatter-aware indexing, and incremental reindexing.
Axon copilot-instructions.md
Instructions for jyunming/Axon, covering axon knowledge center — copilot instructions, what axon is, project namespaces, hierarchical projects (up to 5 levels) and merged read-only scopes.
Axon developer.instructions.md
Instructions for jyunming/Axon, covering role: developer, core conventions, document schema — never deviate, config.yaml → dataclass mapping and adding a new loader.
Axon hotfix-responder.instructions.md
Instructions for jyunming/Axon, covering role: hotfix responder, hotfix workflow, 1. identify and scope the incident, 2. branch from main (not develop) and 3. implement the fix.
Axon security-auditor.instructions.md
Instructions for jyunming/Axon, covering role: security auditor, known risk areas in this codebase, 1. bm25 serialization — src/axon/retrievers.py, 2. path traversal — src/axon/api.py /ingest endpoint and 3. dependency cves.