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.
git clone --depth 1 https://github.com/monoes/monomindWrote 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/monoes/monomind/monograph-watch)<a href="https://agentmods.dev/commands/monoes/monomind/monograph-watch"><img src="https://agentmods.dev/badge/commands/monoes/monomind/monograph-watch/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/monoes/monomind/monograph-watch"><img src="https://agentmods.dev/badge/commands/monoes/monomind/monograph-watch.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00029 | $0.00408 |
| Opus 5.5 | $0.00012 | $0.00163 |
| Sonnet 5.5 | $0.00006 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
monograph:monograph-watch 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 yesterday.
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.
What it actually says
monograph watch
Watch for file changes and incrementally rebuild the knowledge graph. Keeps the graph fresh during active development.
Usage
npx monomind monograph watch [options]
Options
| Flag | Short | Type | Default | Description |
|---|---|---|---|---|
--path |
-p |
string | cwd | Root path to watch |
--llm |
— | boolean | false |
Enable LLM enrichment on each rebuild (requires ANTHROPIC_API_KEY) |
Examples
# Watch and rebuild on any file change
npx monomind monograph watch
# Watch with Claude semantic enrichment on each rebuild
npx monomind monograph watch --llm
# Watch a specific path
npx monomind monograph watch -p ./docs
Behavior
- Runs until
Ctrl+C - Detects changes to code files, markdown, text, RST, and PDFs
- Triggers incremental rebuild (only changed files re-processed)
- Outputs progress per phase as changes are detected
When to Use
- During active documentation writing — graph stays current as you write
- During refactoring — relationships update as imports change
- CI environments — run in background to keep graph fresh for search queries
MCP Tools
// Start watch via MCP
mcp__monomind__monograph_watch({ path: "./" })
// Stop watch via MCP
mcp__monomind__monograph_watch_stop()
See Also
monograph build— one-time full buildmonograph wiki— doc-focused buildmonograph stats— check current graph state
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.
- yesterday First seen · 64 lines · 29 tokens per session scan A 0daa5b2d7eaa
monograph:monograph-watch is a command published in the GitHub repository monoes/monomind (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 29 tokens to every session and 408 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-26.
Other commands, from other repositories
claude-flow-memory
Interact with Claude-Flow memory system.
sessions
Manage OpenAI Codex session history, aliases, and session metadata.
checkpoint
Create an identified recovery point and inspect exact restoration differences.
recall
Retrieve scoped lessons and evaluate their assumptions, conflicts, and applicability.
retro
Write this session's lessons into the project's lessons/ directory using the memory-discipline format.
save-session
Save current session state to a dated file in /.codex/session-data/ so work can be resumed in a future session with full context.