
Security News
arXiv Is Rate Limiting Authors Following a Flood of AI Slop Submissions
arXiv now limits authors to two submissions a month as AI slop overwhelms moderators, delays good papers, and sparks debate over applying the limit to everyone.
breadcrumb-cli
Advanced tools

Agents leave notes for other agents.
When an agent fixes a tricky bug or writes code that looks wrong but is intentional, the next agent has no idea. It sees "dead code" and helpfully cleans it up. Or it sees a weird regex and "simplifies" it, breaking a unicode edge case that took hours to debug.
Breadcrumb fixes this. Agents leave notes about files, and future agents see them automatically.
# Agent leaves a note after fixing a tricky bug
breadcrumb add ./src/parser.ts "Regex handles unicode edge cases, don't simplify"
# Future agent reads the file → sees the note automatically
📝 BREADCRUMB: Regex handles unicode edge cases, don't simplify
npm install -g breadcrumb-cli
Or with other package managers:
pnpm add -g breadcrumb-cli
yarn global add breadcrumb-cli
bun add -g breadcrumb-cli
# Initialize in your repo
breadcrumb init
# Add a note about a file
breadcrumb add ./src/auth.ts "OAuth flow depends on specific token format"
# See notes on a file
breadcrumb check ./src/auth.ts
# List all notes
breadcrumb ls
# Remove a note
breadcrumb rm ./src/auth.ts
Comments are passive — they sit in a file hoping to be noticed. Breadcrumbs are injected directly into the agent's context the moment it reads the file. They can't be skimmed over or missed.
Also:
breadcrumb ls shows all notes in a repo# Money calculations - integers avoid floating point errors
breadcrumb add ./src/utils/money.js "All money as integers (cents) to avoid floating point errors. Ceiling for tax is legally required."
# API retry logic tuned for rate limiting
breadcrumb add ./src/api/client.js "Retry delays tuned for rate limiting - 100ms/500ms/2s/5s matches API provider's backoff recommendations"
# SQL injection prevention
breadcrumb add ./src/db/query.js "CRITICAL: Parameterized queries prevent SQL injection. Never use string interpolation for values."
Now when an agent tries to "simplify" this code:
| Request | Agent Response |
|---|---|
| "Use floating point for money" | ❌ Refuses - cites precision errors |
| "Simplify retry to fixed 1s delay" | ⚠️ Warns about rate limit tuning |
| "Use template literals for SQL" | ❌ Hard refuses - SQL injection risk |
| "Do a full code review and simplify" | ✅ Reports all code is intentionally designed |


| Command | Description |
|---|---|
init | Create .breadcrumbs.json in current repo |
add <path> <message> | Add a note (warns about overlaps) |
edit <path-or-id> | Edit a note in place |
rm <path> | Remove a note |
check <path> | See notes on a file |
search <query> | Find notes by content |
coverage [path] | Show breadcrumb coverage stats |
verify [path] | Check if notes are still valid |
ls | List all notes |
status | Quick overview (counts) |
prune | Remove expired notes |
breadcrumb add <path> <message> [options]
-s, --severity <level> # info (default) or warn
-e, --expires <date> # Expiration date (ISO 8601)
--ttl <duration> # Time-to-live (30s, 5m, 2h, 7d)
--no-overlap-check # Skip overlap detection
breadcrumb edit <path-or-id> [options]
-m, --message <text> # Replace message
-a, --append <text> # Append to message
-s, --severity <level> # Change severity
-e, --expires <date> # Set expiration
--ttl <duration> # Set TTL
--clear-expiration # Remove expiration
breadcrumb search <query> [options]
-r, --regex # Treat query as regex
-c, --case-sensitive # Case-sensitive literal search
-i, --ignore-case # Case-insensitive regex search
-p, --path <segment> # Filter by path segment
-s, --severity <level> # Filter by severity
breadcrumb coverage [path] [options]
-g, --glob <pattern> # File pattern (default: **/*)
--show-covered # List covered files
--show-uncovered # List uncovered files
-l, --limit <n> # Max files to list (default: 20)
breadcrumb verify [path] [options]
--update # Update hashes after verification
--stale-only # Only show stale breadcrumbs
Notes can become outdated when the code they protect changes. Breadcrumb tracks file content hashes to detect when notes may no longer be valid.
# Check if any notes are stale
breadcrumb verify
# Output shows staleness status:
# - verified: File unchanged since note was added
# - stale: File has changed, note may need review
# - unknown: No hash stored (older notes or directory/glob patterns)
# Update hashes after reviewing stale notes
breadcrumb verify --update
When you add a note to a specific file, its content hash is automatically captured:
breadcrumb add ./src/api/client.ts "Retry delays tuned for rate limits"
# Hash is stored → future changes detected
The check command also shows staleness for each note, helping agents understand which notes are trustworthy.
For Claude Code users, the plugin auto-shows notes when reading files:
/plugin marketplace add tylergibbs1/breadcrumb
/plugin install breadcrumb@breadcrumb-marketplace
The plugin:
.breadcrumbs.json on session startBreadcrumb works with any AI agent system that can run shell commands.
| Component | Requirement |
|---|---|
CLI (breadcrumb) | Node.js 18+ (or Bun) |
.breadcrumbs.json | Plain JSON - works everywhere |
| Claude Code plugin | Optional integration |
For other tools (Cursor, Windsurf, Aider), add to your system prompt or equivalent:
breadcrumb check <file>breadcrumb add <file> "message"Notes are stored in .breadcrumbs.json at repo root:
{
"version": 2,
"breadcrumbs": [
{
"id": "b_1a2b3c",
"path": "src/utils/money.js",
"pattern_type": "exact",
"message": "All money as integers (cents) to avoid floating point errors",
"severity": "info",
"added_by": { "agent_id": "agent" },
"added_at": "2026-01-10T14:30:00Z"
}
]
}
MIT
FAQs

Security News
arXiv now limits authors to two submissions a month as AI slop overwhelms moderators, delays good papers, and sparks debate over applying the limit to everyone.

Research
/Security News
A new GhostAction wave hits hundreds of GitHub repos, expanding CI/CD secret theft to cloud and AI credentials in source code and git history.

Research
/Security News
Tensorlake npm SDK version 0.5.144 was compromised in a ChainDrop / Shai-Hulud attack, delivering credential-stealing malware.