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 WazzaMo/vecfs --skill vecfs-memorygit clone --depth 1 https://github.com/WazzaMo/vecfsWrote 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/wazzamo/vecfs/vecfs-memory)<a href="https://agentmods.dev/skills/wazzamo/vecfs/vecfs-memory"><img src="https://agentmods.dev/badge/skills/wazzamo/vecfs/vecfs-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/wazzamo/vecfs/vecfs-memory"><img src="https://agentmods.dev/badge/skills/wazzamo/vecfs/vecfs-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 | $0.01239 |
| Opus 5.5 | $0.00022 | $0.00496 |
| Sonnet 5.5 | $0.00011 | $0.00248 |
| Haiku 4.5 | $0.00005 | $0.00124 |
Grade A, and why
vecfs-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 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.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Activate
Activate this skill when any of the following apply:
- The user's task is non-trivial and could benefit from prior context.
- The user explicitly mentions remembering, recalling, or learning.
- The agent encounters a repeated error or pattern it has seen before.
- The conversation involves a project that spans multiple sessions.
- The conversation or a markdown file indicates that a decision has been made.
Generating Embeddings
The VecFS MCP server accepts pre-computed sparse vectors. Use the bundled embedding script to convert text into a sparse vector before calling the server tools.
Embed a Query (for search)
echo "your search text" | python -m vecfs_embed --mode query
Embed a Document (for memorisation)
python -m vecfs_embed --mode document "key lesson or fact to remember"
The script outputs JSON with a vector field that can be passed directly
to the search or memorize tools.
See references/vector-encoding.md for details on how embeddings are converted to sparse vectors.
Context Sweep (Proactive Recall)
At the start of any non-trivial task, perform a Context Sweep:
- Extract keywords and concepts from the current user prompt.
- Generate a sparse vector by running the embedding script in
querymode. - Call the
searchtool with that vector. - If results are returned with high similarity, incorporate them into your reasoning (including any stored decisions). Mention to the user that you found relevant history.
- If results have low similarity or no results are returned, proceed without historical context. Do not force irrelevant recall.
Memorisation (Reflective Learning)
After completing a task or achieving a milestone:
- Identify key lessons, corrections, decisions, or facts worth retaining.
- Filter for long-term value: avoid storing transient details like one-time commands or session-specific paths.
- Summarise the lesson as a short, clear text (one to three sentences).
- Generate a sparse vector by running the embedding script in
documentmode. - Call the
memorizetool with:- A descriptive
id(e.g.,lesson-react-useeffect-cleanup). - The
textcontent. - The sparse
vector. - Optional
metadatatags (e.g.,{"topic": "react", "type": "correction"}).
- A descriptive
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 150 lines · 54 tokens per session scan A 2c44fd15cc17
vecfs-memory is a skill published in the GitHub repository WazzaMo/vecfs (9 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,239 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 2026-08-31.
Other skills, from other repositories
engram-digest
Seed or top up this project's Engram graph from the existing codebase — an explicit, user-invoked digestion of the current working tree into typed memory nodes (decisions, principles, cautions, problems, insights, intents). Use when the user says "digest this project", "ingest the codebase into memory", "seed the…
engram
Read and write the project's durable reasoning memory (decisions, principles, cautions, problems, insights) through the Engram MCP tools. Recall relevant memory before non-trivial work; capture only durable, high-value knowledge silently at natural stopping points; keep the graph honest (judge suspects, close answered…
relic
A system for turning people, pets, relationships, teams, places, moments, or other subjects into interactive digital profiles called Relics. It can also let users interact with existing profiles and includes separate steps for creating and protecting them.
thoughtline-memory
Persistent, project-aware memory for AI coding agents. Use thoughtline whenever you make a decision, fix a bug, learn something non-obvious, or need to recall prior work.
context-window-optimizer
Curates and condenses codebase context, file contents, and prompts to optimize LLM token usage and response quality.
bootstrap-llm-synthesis
Construct the LLM synthesis prompt from project surface scan + optional tree-sitter context + optional Q&A answers. Call the LLM. Parse and validate the response into 6-8 structured memory entries with clarity tags and source traceability. Used as Stage 3 of the /gaai:bootstrap pipeline.