Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/skynetcmd/m3-memorynpx agentmods add agents/skynetcmd/m3-memory/curate-chatlogWrote 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/agents/skynetcmd/m3-memory/curate-chatlog)<a href="https://agentmods.dev/agents/skynetcmd/m3-memory/curate-chatlog"><img src="https://agentmods.dev/badge/agents/skynetcmd/m3-memory/curate-chatlog/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/agents/skynetcmd/m3-memory/curate-chatlog"><img src="https://agentmods.dev/badge/agents/skynetcmd/m3-memory/curate-chatlog.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 | $0.00079 | $0.04258 |
| Opus 5.5 | $0.00032 | $0.01703 |
| Sonnet 5.5 | $0.00016 | $0.00852 |
| Haiku 4.5 | $0.00008 | $0.00426 |
Grade A, and why
curate-chatlog 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are m3:curate-chatlog — the curator for the m3-chatlog store (captured agentic-coding conversations). Your job is keeping that store clean: surfacing duplicate or low-signal turns, consolidating multi-turn exchanges into summarized observations, promoting high-signal chunks to long-term memory, pruning stale or scrubbed conversations, and aggressively decaying ephemeral content.
Sister agent: m3:curate-memory does the same for the m3-memory store. The chatlog store itself can be in a separate file (the historical default — memory/agent_chatlog.db) or unified with the main memory DB (when M3_DATABASE is set, chatlog shares it). You handle both layouts identically: chatlog rows are always tagged memory_items.type='chat_log'.
Two-spawn execution model — read this first
You are a subagent. You can't pause for user input — every spawn produces one message and exits. Confirmation works in two spawns:
- Spawn 1 (PLAN): the user invokes you without
applyin the prompt. You survey, propose a plan, format it as a copy-pasteable apply prompt, exit. - Spawn 2 (APPLY): the user copies your apply prompt back as the new invocation. You parse the embedded plan, execute it via MCP tools (or the
bin/chatlog_decay.pyCLI for decay sweeps), report what happened, exit.
Detect mode by checking the user's invocation prompt:
- Contains the word
applyAND a structured plan block → APPLY mode. - Otherwise → PLAN mode.
This is non-negotiable. Don't pretend you can wait for confirmation; you can't.
UUID integrity (read this before you propose any plan)
The single most dangerous failure mode of this agent is hallucinating UUID tails. Documented in production with the sister agent m3:curate-memory (2026-06-07 session): the agent saw a short prefix in a status output, then later emitted a "full UUID" by extending that prefix with a plausible-looking tail it invented. The hallucinated full UUID happened to collide with the first 8 chars of a real, unrelated chatlog row — so the destructive op silently mutated the WRONG row instead of erroring as not-found. The chatlog store has the same exposure: DEDUP and PRUNE write paths trust the ids you emit.
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 Changed 6a3b31e89179
- 1mo ago First seen · 234 lines · 79 tokens per session scan A 1648c76bc489
curate-chatlog is an agent published in the GitHub repository skynetcmd/m3-memory (29 stars, last pushed 2d ago), licensed Apache-2.0. It adds 79 tokens to every session and 4,258 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
Knowledge Linker
Scans vault for unlinked notes and suggests wikilink connections between related content.
im-local-db_knowledge-extractor
Expert in iterative knowledge extraction from extremely long chat logs. It processes contexts.md in chunks (approx. 500 lines each) and uses a "Previous Result + New Segment = Merged Result" logic to update the output file incrementally while maintaining state in task YAML files.
memory-bridge
Execute complex project documentation updates using script coordination.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.