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.
Borrowing it
Nothing to install: this file belongs to vectorize-io/hindsight. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vectorize-io/hindsight/main/.claude/skills/figure/SKILL.mdgit 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/figure)<a href="https://agentmods.dev/skills/vectorize-io/hindsight/figure"><img src="https://agentmods.dev/badge/skills/vectorize-io/hindsight/figure/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/figure"><img src="https://agentmods.dev/badge/skills/vectorize-io/hindsight/figure.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 | $0.00093 | $0.02198 |
| Opus 5.5 | $0.00037 | $0.00879 |
| Sonnet 5.5 | $0.00019 | $0.00440 |
| Haiku 4.5 | $0.00009 | $0.00220 |
Grade A, and why
figure 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 9d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figure
One animated SVG, no scripts, no upload: it renders and plays anywhere markdown does — GitHub README, PR and issue comments, blog posts, Notion. Sharp at any size, and it follows the reader's light or dark theme.
Figures are Giotto diagrams: one JSON document, the same
format the docs site's interactive figures use (hindsight-docs/figures/*.json).
You write the diagram JSON — never SVG. One command renders it. No build, no browser.
1. Write the diagram
Do not save it as a file in the repo. It is an input, not a deliverable — pipe it in (step 2), and the rendered SVG keeps a copy of it for you.
{
"title": "Retain",
"speed": 2000,
"elements": [
{ "id": "root", "type": "group", "children": ["agent", "api", "bank"], "layout": { "direction": "row", "gap": 48 } },
{ "id": "agent", "type": "rectangle", "content": [{ "type": "title", "text": "Your AI Agent" }] },
{ "id": "api", "type": "group", "label": { "title": "Hindsight API" }, "children": ["retain"], "layout": { "direction": "column", "gap": 24 } },
{ "id": "retain", "type": "rectangle", "content": [{ "type": "title", "text": "Retain" }, { "type": "subtitle", "text": "LLM extraction" }] },
{ "id": "bank", "type": "group", "label": { "title": "Memory Bank" }, "children": ["facts", "obs"], "layout": { "direction": "column", "gap": 28 } },
{ "id": "facts", "type": "cylinder", "content": [{ "type": "title", "text": "Facts" }, { "type": "subtitle", "text": "world · experience" }] },
{ "id": "obs", "type": "cylinder", "content": [{ "type": "title", "text": "Observations" }] },
{ "id": "call", "type": "arrow", "route": "curved", "start": { "id": "agent" }, "end": { "id": "retain" }, "label": { "text": "retain()" } },
{ "id": "store", "type": "arrow", "route": "curved", "start": { "id": "retain" }, "end": { "id": "facts" }, "label": { "text": "extract" } },
{ "id": "consolidate", "type": "arrow", "route": "curved", "start": { "id": "facts" }, "end": { "id": "obs" }, "label": { "text": "consolidate" }, "quiet": true }
],
"scenes": [
{
"label": "retain()",
"beats": [
{ "edges": { "edge": "call", "data": "“Alice joined Google in March”" }, "say": "Your agent sends what happened." },
{
"edges": "store",
"show": { "facts": [{ "tag": "world", "tone": "blue", "text": "Alice joined Google", "meta": "Mar 2026", "mark": "new" }] },
"say": "An LLM pulls out the facts."
},
{
"edges": "consolidate",
"ms": 2600,
"show": { "obs": [{ "text": "Alice works at Google", "meta": "2 sources" }] },
"say": "The worker merges them into one belief."
}
]
}
]
}
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.
- 9d ago Changed · -27 lines · +6 tokens per session 7f93dcbfbde2
- 22d ago First seen · 175 lines · 87 tokens per session scan A dad0cadba9b3
figure is a skill published in the GitHub repository vectorize-io/hindsight (50,509 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 2,198 once invoked, about $0.0004 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 2026-09-25.
Other skills, from other repositories
paperclip-capsules
Generate, implement, or review Paperclip capsule visuals. Use for capsule art, agent capsules, heartbeat status capsules, identicons, capsule banks, or brand-usage validation.
design-critique
Run a heuristic evaluation of a UI design (image, HTML, Figma, URL, or flow) the way an experienced designer would. Evaluates 4 categories (Visual & hierarchy, Usability & interaction, Accessibility, Content) using recognized frameworks, NN/g 0-4 severity, and evaluability-aware prioritization that never judges what…
persistent-notes
Save notes locally to /mnt/workspace/notes.json file. Use when user wants to "save a note" or "remember something".
dashboard-template
Kiro Crew repo only: load this when a task will author or change a dashboard page. A page never ships alone: the same PR carries its TypedDict contract, its provider, and a parity test that the two agree. Scaffold all four from one field list; read numbers from an existing fold, never type them.
theme-pack-authoring
Build, validate, and install Kiro Crew theme packs -- pack anatomy, the 56-variable palette, role-tagged fonts, the overrides.css allowlist (what installs vs what actually renders), and the install-verify cycle. Use when the user wants to create or edit a theme pack.
image-authoring
Author images and diagrams as code — SVG, Pillow, Excalidraw, mermaid. Load when asked to draw, illustrate, or make an image, icon, logo, poster, or diagram.