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/hatefsystems/search-engine-core/mongodb-bsongit clone --depth 1 https://github.com/hatefsystems/search-engine-coreWhat 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 | $0.00856 | $0.00856 |
| Opus 5 | $0.00428 | $0.00428 |
| Sonnet 5 | $0.00171 | $0.00171 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
search-engine-core mongodb-bson.instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MongoDB C++ Rules
Instance Initialization
// ❌ WRONG - Crashes
mongocxx::uri uri{"mongodb://localhost:27017"};
client_ = std::make_unique<mongocxx::client>(uri);
// ✅ CORRECT
#include "../../include/mongodb.h"
mongocxx::instance& instance = MongoDBInstance::getInstance();
mongocxx::uri uri{"mongodb://localhost:27017"};
client_ = std::make_unique<mongocxx::client>(uri);
BSON: Use Basic Builder for Complex Documents
Never use stream builder for nested documents or updates — it causes data corruption.
// ❌ WRONG - Stream builder corrupts; ALL FIELDS GET DELETED
document setDoc{};
setDoc << "field1" << value1 << "field2" << value2; // Not finalized!
document updateDoc{};
updateDoc << "$set" << setDoc << finalize; // Passing unfinalized doc!
// Result: document becomes { _id: ObjectId(...) } - ALL DATA LOST!
// ✅ CORRECT - Basic builder
using bsoncxx::builder::basic::kvp;
auto setFields = bsoncxx::builder::basic::document{};
setFields.append(kvp("field1", value1));
setFields.append(kvp("field2", value2));
auto updateDoc = bsoncxx::builder::basic::document{};
updateDoc.append(kvp("$set", setFields.extract()));
collection.update_one(filter, updateDoc.extract());
- Use basic builder for
$set,$push,$pull, nested docs. - Call
.extract()on each subdocument before adding to parent. - Stream builder ONLY for simple, flat filters (e.g.
document{} << "email" << "[email protected]" << "active" << true << finalizefor find_one).
When to Use Each Builder
| Use Case | Builder | Why |
|---|---|---|
Complex updates ($set, $push, etc.) |
Basic Builder | Prevents data corruption |
| Nested documents (arrays, subdocuments) | Basic Builder | Explicit extraction required |
| Multiple operators in one update | Basic Builder | Safer composition |
| Simple flat queries/filters | Stream Builder | More concise |
| Production database operations | Basic Builder | Safer and maintainable |
DON'T: Mix Builder Types
// ❌ BAD
document streamDoc{};
basic::document basicDoc{};
streamDoc << "$set" << basicDoc; // Wrong!
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 · 102 lines · 856 tokens per session scan A 7a1d54df9b26
search-engine-core mongodb-bson.instructions.md is an instructions file published in the GitHub repository hatefsystems/search-engine-core (5 stars, last pushed 28d ago), licensed Apache-2.0. It adds 856 tokens to every session, about $0.0043 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
Xapiand AGENTS.md
Instructions for Kronuz/Xapiand, covering agents.md — working in the xapiand codebase, first, the big split: own code vs. vendored, where things live, build & toggles and verifying changes end-to-end (the docs are a test suite).
electron CLAUDE.md
Instructions for electron/electron, covering electron development guide, running nodemodules binaries, project overview, directory structure and build tools setup.
electron copilot-instructions.md
Instructions for electron/electron, covering copilot instructions for electron, build system, linting, running a single test and example: npm run test -- -g "ipc".
compiler-explorer AGENTS.md
Instructions for compiler-explorer/compiler-explorer, covering agents.md, build & test commands, important workflow requirements, style guidelines and architecture guidelines.
weaviate CLAUDE.md
Claude Code instructions for weaviate/weaviate, covering claude.md, no bug is ever out of scope, build & run, build the binary (cgoenabled=0, static linking) and build debug binary (with delve support).
compiler-explorer copilot-instructions.md
Instructions for compiler-explorer/compiler-explorer: For each answer to the user, evaluate your level of confidence in the correctness of the answer on a scale from 1 to 10, where 1 is very uncertain and 10 is absolutely certain. If your confidence level is below 8, state so and suggest ways to verify the answer.