A command that saves useful long-term details from the current session to Trailmem, a memory store for later sessions. It focuses on decisions, lessons, follow-up tasks, and lasting preferences.

Use it at the end of a session to record durable decisions, known issues, open work, constraints, or user preferences while they are still available.

It preserves important context before the session ends, when a later automatic hook would no longer have access to the conversation.

tm-save — Command for Claude Code by amitnexTech/trailmem

Install

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.

Clone the repo

git clone --depth 1 https://github.com/amitnexTech/trailmem

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/amitnextech/trailmem/tm-save/github.svg)](https://agentmods.dev/commands/amitnextech/trailmem/tm-save)

Your own site

<a href="https://agentmods.dev/commands/amitnextech/trailmem/tm-save"><img src="https://agentmods.dev/badge/commands/amitnextech/trailmem/tm-save/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/amitnextech/trailmem/tm-save"><img src="https://agentmods.dev/badge/commands/amitnextech/trailmem/tm-save.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 368 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00013	$0.00368
Opus 5.5	$0.00005	$0.00147
Sonnet 5.5	$0.00003	$0.00074
Haiku 4.5	$0.00001	$0.00037

Measured 1mo ago against content hash 91adbc975943, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tm-save 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 1mo 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.

trailmem/commands/tm-save.md · 34 lines

What it actually says

Capture the durable memory from THIS session into trailmem now, while the full conversation is still in context. A host end-of-session hook cannot do this — it runs after you are gone and never sees the conversation — so this is the reliable capture point.

Do the following:

Review the conversation and identify what is worth persisting across sessions:
- decisions — a rule, tool choice, structure, or enforced behavior we settled on
- lesson — a bug, mistake, or non-obvious thing learned (include the why)
- task — concrete follow-up work that is still open
- constraint / user_preference — a durable rule or personal preference Skip ephemeral chatter, things already stored, and anything derivable from code or git history.
For each item, call trailmem_store with:
- content in English (this is a hard rule even if we spoke another language),
- the correct event_type from the list above,
- a link to a related existing memory (link_to + edge_type) so it is not an orphan — query first if unsure what to link to.
Respect dedup: if trailmem_store reports a near-duplicate, update the existing memory with trailmem_edit instead of forcing a second copy.
If nothing this session is genuinely worth persisting, say so plainly ("nothing durable to save this session") — do NOT invent filler memories.

After saving, give a one-line summary of what you stored (ids + titles) so the user can confirm before exiting.

Changes

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.

1mo ago First seen · 34 lines · 13 tokens per session scan A 91adbc975943

Subscribe to this mod's changes

tm-save is a command published in the GitHub repository amitnexTech/trailmem (1 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 368 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 2026-08-31.

Memory and context ai-agents claude embeddings knowledge-graph local-first mcp

slm-remember

Capture durable facts, decisions, constraints, and gotchas into SuperLocalMemory. Use when the user says "remember that", "save this decision", "note this constraint", or when a session produces a conclusion worth persisting across sessions. Always recall first to avoid duplicates.

qualixar/superlocalmemory · 60 tokens

slm-status

Health and optimization stats for SuperLocalMemory — call slmoptimizestats() for live compression and cache counters (compressruns, tokenssavedcompress, cacheproxyhits, cacheproxymisses, cachekvhits, cachekvmisses); run slm status [--json] for system state (mode, profile, DB size, fact/entity/edge counts) and slm…

qualixar/superlocalmemory · 112 tokens

slm-media

Save pictures and PDFs in SuperLocalMemory and find them again by describing them. Covers when to save a picture or document, remembermedia, rememberdocument, getmedia, mediastatus and mediauploadlink, how recall returns pictures and PDF pages, the limits, what stays private, turning the feature on with slm media (16…

qualixar/superlocalmemory · 101 tokens

slm-session

Manage SuperLocalMemory session lifecycle — call sessioninit once at the start of every fresh session to load relevant project context and get a sessionid; call closesession when work is meaningfully complete to commit temporal summaries. Correct lifecycle hygiene is what makes SLM's learning loop work.

qualixar/superlocalmemory · 60 tokens

slm-bot-memory

Cross-bot memory on a shared computer (Grok Bot, Cursor plugin, any host where several agents share one machine). Explains agentid attribution vs. profile/scope access, how to namespace by agentid + profile + scope, and what must never be written to memory. Read this before the first remember/recall on a new…

qualixar/superlocalmemory · 82 tokens

slm-getting-started-bot

First-session orientation for SuperLocalMemory on a headless bot host (Grok Bot, or any Cursor-format plugin install with no hooks, no dashboard, and no interactive setup wizard). What is different here vs. Claude Code/Codex, which 19 tools are actually available, and the first three calls to make.

qualixar/superlocalmemory · 74 tokens