vision-memory-mcp

vision-memory-mcp is a skill for Claude Code, Codex from putervision/state-memory-mcp. It costs 34 tokens per session (1,401 once invoked), scanned B, original, MIT.

A workflow for using a visual-memory server to store screenshots and page states. It helps an agent recognize layouts it has already seen and track how screens change after actions.

In plain words
What is it for?
Use it when inspecting webpages or applications, verifying screenshots, recording clicks or navigation, and saving visual milestones. It can search stored visual states and record action outcomes.
Why use it?
It avoids repeatedly analyzing the same screenshot and preserves context across visual checks. This can reduce duplicate vision work and make navigation changes traceable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

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.

agentmods
npx agentmods add skills/putervision/state-memory-mcp/vision-memory-mcp
Any agent
npx skills add putervision/state-memory-mcp --skill vision-memory-mcp
Clone the repo
git clone --depth 1 https://github.com/putervision/state-memory-mcp

Made for: Claude Code, Codex.

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.

agentmods badge for vision-memory-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/putervision/state-memory-mcp/vision-memory-mcp.svg)](https://agentmods.dev/skills/putervision/state-memory-mcp/vision-memory-mcp)
Your own site
<a href="https://agentmods.dev/skills/putervision/state-memory-mcp/vision-memory-mcp"><img src="https://agentmods.dev/badge/skills/putervision/state-memory-mcp/vision-memory-mcp.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,401 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.01401
Opus 5 $0.00017 $0.00700
Sonnet 5 $0.00007 $0.00280
Haiku 4.5 $0.00003 $0.00140

Measured 6d ago against content hash 2babda58358c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

vision-memory-mcp scanned grade B with 1 finding 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 6d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

* **Google Antigravity (`~/.gemini/config/config.json`)**: Add these rules to your `"globalPermissionGrants"` -> `"allow"` list:
Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.agents/skills/vision-memory-mcp/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual Memory (vision-memory-mcp)

This project utilizes vision-memory-mcp to cache visual states, record layout transitions, and avoid repetitive LLM vision calls.

1. Priority Order & Checklist

Whenever you capture a screenshot, examine a webpage, or need to verify a visual state, you MUST run this sequence:

  1. Orient: Call get_session_context to load active transitions and recent visual states.
  2. Search (Optional): Call recall_memory to search past visual states by text query or image query.
  3. Ingest/Verify: Call analyze_screenshot with the base64 screenshot before calling any vision LLMs.
  4. Cache Hit: If is_known is true, read the returned description and do NOT call your vision LLM.
  5. Cache Miss: If is_known is false, inspect the image with your vision model, summarize the layout, and register it back by calling analyze_screenshot with both the screenshot and description parameters.
  6. Log Transitions: Right after taking any UI action (click, type, navigate, scroll), call record_outcome to build the navigation graph.
  7. Snapshotting: Call manage_snapshot (action: "save") when reaching milestones, and manage_snapshot (action: "diff") to check for visual regressions.

2. Complete Tool Reference

Tool Name Key Inputs Description
analyze_screenshot screenshot? (base64), file_path?, description?, items? Main ingestion (single or batch) and visual state retrieval tool.
recall_memory query?, screenshot?, file_path?, strategy?, limit? Search visual memory by text query or image query (read-only).
record_outcome from_state_id, to_state_id?, action, action_type? ('blocker' | 'click' | etc.) Record UI action transitions or log visual blockers for state-memory.
get_navigation_paths from_state_id?, to_state_id?, to_description?, max_hops? Find historical path or instructions between states.
predict_next_action current_state_id, goal_description?, goal_state_id? Predict best next UI action and grounded element handles (target_selector, target_coords).
compare_states state_a_id & state_b_id OR video_a_id & video_b_id Compare two states visually (has_layout_change) or compare video runs.
get_session_context include_recent?, include_frequent? Get recent/frequent states, transition graphs, disk stats, cache metrics, and version info.
manage_snapshot action ('save' | 'diff' | 'export' | 'restore'), name?, archive_json? Unified snapshot management for visual checkpoints and regression detection.
manage_visual_spec action ('set' | 'verify' | 'list'), name?, screenshot?, tolerance? Register and verify visual design contract baselines (Visual SDD).
manage_video action ('ingest' | 'search' | 'timeline'), file_path?, query?, video_id? Ingest WebM/MP4 recordings, search video keyframes, or retrieve timelines.
create_evidence_pack keyframe_state_ids, source_video_id?, linked_state_memory_nodes? Package immutable evidence packs linking video keyframes to state-memory DAGs.
export_trajectories format? ('json' | 'llava' | 'qwen2_vl' | 'joint'), trace_id? Export multimodal trajectories for model fine-tuning or joint workflow exports.
undo_visual_mutation type? ('state' | 'transition' | 'any') Revert the last visual state ingestion or transition edge addition.
forget_state state_id Purge a specific state and vector embedding for privacy.
wait_for_visual_state target_state_id, timeout_ms? Poll for target visual state until present or timeout occurs.

Read the full file on GitHub · 58 lines

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.

  1. 6d ago First seen · 58 lines · 34 tokens per session scan B 2babda58358c

Subscribe to this mod's changes

vision-memory-mcp is a skill published in the GitHub repository putervision/state-memory-mcp (79 stars, last pushed 17d ago), licensed MIT. It adds 34 tokens to every session and 1,401 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

cortex-remember-global

Store a global memory that is visible across all projects. Use when the user shares architecture rules, coding conventions, infrastructure facts, security policies, team agreements, or any knowledge that applies beyond a single project. Triggers on 'remember this everywhere', 'this applies to all projects', 'global…

cdeust/Cortex · 99 tokens

cortex-automate

Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…

cdeust/Cortex · 93 tokens

cortex-consolidate

Run memory maintenance — decay old memories, compress stale content, consolidate episodic memories into semantic knowledge, and run sleep-like replay. Use when the user says 'clean up memories', 'consolidate', 'run maintenance', 'compress old memories', 'memory cleanup', or periodically to keep the memory system…

cdeust/Cortex · 84 tokens

cortex-debug-memory

Debug and fix memory system issues — validate memories, rate quality, manage protection, forget bad memories, and restore from checkpoints. Use when the user says 'fix memory', 'bad memory', 'wrong memory', 'delete this', 'protect this', 'this memory is wrong', 'memory quality', 'rate this memory', 'restore…

cdeust/Cortex · 87 tokens

cortex-explore-memory

Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you…

cdeust/Cortex · 91 tokens

cortex-navigate-knowledge

Navigate the knowledge graph — trace entity relationships, explore causal chains, drill into memory clusters, and traverse co-access paths. Use when the user asks 'how are these related', 'what connects X to Y', 'show me the knowledge graph', 'trace the relationship', 'what caused X', 'drill down into', 'explore…

cdeust/Cortex · 95 tokens