Memento-Skills is an agent runtime and skill framework in which agents can create, reuse, execute, reflect on, and repair persistent skills. It is intended for multi-step task execution, research, planning, and building reusable agent behaviour through a desktop application or public runtime. The catalogue entries are examples of skills and agents built for this framework.
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 Memento-Teams/Memento-Skills --skill filesystemgit clone --depth 1 https://github.com/Memento-Teams/Memento-SkillsWrote 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/memento-teams/memento-skills/filesystem)<a href="https://agentmods.dev/skills/memento-teams/memento-skills/filesystem"><img src="https://agentmods.dev/badge/skills/memento-teams/memento-skills/filesystem/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/memento-teams/memento-skills/filesystem"><img src="https://agentmods.dev/badge/skills/memento-teams/memento-skills/filesystem.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00024 | $0.00664 |
| Opus 5 | $0.00012 | $0.00332 |
| Sonnet 5 | $0.00005 | $0.00133 |
| Haiku 4.5 | $0.00002 | $0.00066 |
Grade A, and why
filesystem 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 11d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Filesystem Skill
Overview
Direct filesystem operations without external dependencies. Read, write, edit, list, copy, move, and search files.
Usage
Use the available builtin tools to perform file operations directly. Commonly used tools for this skill are: list_dir, read_file, file_create, edit_file_by_lines, grep, and bash.
When the task requires programmatic/structured processing (e.g., parsing complex formats or batch transformations), python_repl can be used as an advanced fallback.
- Paths can be absolute or relative to working_dir
- Parent directories are created automatically for write operations
- For complex file operations not covered by builtin tools, use
bash
Common Recipes
JSON
import json
# Read
with open('data.json', 'r', encoding='utf-8') as f:
data = json.load(f)
# Write (pretty-printed)
with open('output.json', 'w', encoding='utf-8') as f:
json.dump(data, f, indent=2, ensure_ascii=False)
CSV
import csv
# Read
with open('data.csv', 'r', encoding='utf-8') as f:
reader = csv.DictReader(f)
for row in reader:
print(row)
# Write
with open('output.csv', 'w', newline='', encoding='utf-8') as f:
writer = csv.DictWriter(f, fieldnames=['name', 'value'])
writer.writeheader()
writer.writerows([{'name': 'a', 'value': 1}])
YAML
# Requires: pip install pyyaml
import yaml
# Read
with open('config.yaml', 'r') as f:
data = yaml.safe_load(f)
# Write
with open('output.yaml', 'w') as f:
yaml.dump(data, f, default_flow_style=False, allow_unicode=True)
Directory Operations
# List files recursively
find . -type f -name "*.py"
# Directory size
du -sh /path/to/dir
# Copy directory
cp -r src/ dst/
# Move/rename
mv old_name.txt new_name.txt
File Search
# Search file contents (grep)
grep -r "search_term" --include="*.py" .
# Find files by name
find . -name "*.log" -mtime -7 # Modified in last 7 days
# Count lines
wc -l *.py
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.
- 11d ago First seen · 115 lines · 24 tokens per session scan A 76e4299c5310
filesystem is a skill published in the GitHub repository Memento-Teams/Memento-Skills (1,555 stars, last pushed 25d ago), licensed Apache-2.0. It adds 24 tokens to every session and 664 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…