vectorize-io/hindsight is an agent memory system that stores experiences and helps AI agents learn over time instead of only recalling conversation history. It is used by developers adding long-term memory to agents, including coding agents. Catalogue add-ons connect agents to Hindsight and its memory workflows.
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 skills add vectorize-io/hindsight --skill routine-memorygit clone --depth 1 https://github.com/vectorize-io/hindsightWrote 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/skills/vectorize-io/hindsight/routine-memory)<a href="https://agentmods.dev/skills/vectorize-io/hindsight/routine-memory"><img src="https://agentmods.dev/badge/skills/vectorize-io/hindsight/routine-memory/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/skills/vectorize-io/hindsight/routine-memory"><img src="https://agentmods.dev/badge/skills/vectorize-io/hindsight/routine-memory.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 | $0.00054 | $0.00382 |
| Opus 5.5 | $0.00022 | $0.00153 |
| Sonnet 5.5 | $0.00011 | $0.00076 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
routine-memory 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 13d 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.
What it actually says
Remember between routine runs
A routine runs again and again. Without memory each run starts from zero, repeats work and misses what changed. Read the last run before starting, and record this run before finishing.
When creating or editing a routine
Write the memory steps into the routine's own instructions, so every run carries them even when nobody is in the chat:
- First: "Recall the last run of from Hindsight and use it."
- Last: "Retain a run note to Hindsight: what this run found, what changed, and what the next run should check first."
Tell the user you added them.
At the start of the run
- Call
recallon this Bot's bank with the query "last run of ". - Use it: skip what was already handled, pick up what was left open, and compare against what the last run found.
At the end of the run
- Call
retainon this Bot's bank with a note covering: the routine name, the date, what this run found, what changed since the last run, and what the next run should check first. Retain a note even when nothing changed, so the next run knows when this one looked. - Use the tags
source:grok-bot,bot:<bot-name>androutine:<routine name>. - If the run found something other Bots should act on, also retain it to
grok-bot::shared(see thebot-handoffskill).
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.
- 13d ago First seen · 29 lines · 54 tokens per session scan A 457f8a6d7dfd
routine-memory is a skill published in the GitHub repository vectorize-io/hindsight (50,054 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 382 once invoked, about $0.0002 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 2026-10-03.
Other skills, from other repositories
persistent-notes
Save notes locally to /mnt/workspace/notes.json file. Use when user wants to "save a note" or "remember something".
session-summaries
What the chat right-panel session summary shows, what it costs, and how to make a session summarize well. Load when the user asks about the session summary panel, why a summary looks wrong or empty, or how to turn it on.
semantix
Install and use the semantix memory kernel as a middleware in your agent: extract user preferences / workflows / experience from past sessions, retrieve and inject them on demand. One binary + your agent's own tools.
search-shared-sessions
Search an Agent Relay workspace's shared coding-agent sessions for prior work, decisions, fixes, or the context behind a task or pull request. Use when team history could answer the user's question or prevent repeating an investigation.
memory-audit-belief-duel
A guided review process for conflicting beliefs or memories. It examines cases where two conclusions cannot both be true, including conflicts between a general rule and a more specific memory.
memory-audit-discoverability
A review guide for checking whether stored memories can be found at the right time. It focuses on where memories are attached, when they are triggered, whether aliases are missing, and whether a parent has too many children.