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 caiowilson/MCP-memento --skill handoffgit clone --depth 1 https://github.com/caiowilson/MCP-mementoWrote 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/caiowilson/mcp-memento/handoff)<a href="https://agentmods.dev/skills/caiowilson/mcp-memento/handoff"><img src="https://agentmods.dev/badge/skills/caiowilson/mcp-memento/handoff/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/caiowilson/mcp-memento/handoff"><img src="https://agentmods.dev/badge/skills/caiowilson/mcp-memento/handoff.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 | $0.00059 | $0.00501 |
| Opus 5.5 | $0.00024 | $0.00200 |
| Sonnet 5.5 | $0.00012 | $0.00100 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade A, and why
handoff 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 2mo 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
Create a visible handoff
Use this storage contract:
- Default target:
<repository-root>/MEMENTO_HANDOFF.md. - Format: plain Markdown with the sections below.
- Operation: create the file, or replace its existing handoff after reading it.
- Visibility: never use hidden files,
.claude/, Git metadata, caches, MCP memory, or any second storage location. - Filesystem boundary: abort if the target is a symbolic link or, when it exists, is not a regular file. Never follow a link for reading or writing.
Gather evidence with read-only tools: repository instructions, git status --short, staged and unstaged diff statistics with --no-ext-diff, and focused reads of changed files. Never enable external diff drivers. Draft:
# Repository Handoff
## Goal
## Done
## Relevant files
## Decisions
## Constraints
## Tried and learned
## Next steps
## Validate
## Risks
Before reading an existing target, check it without following links: reject it when test -L succeeds; when test -e succeeds, require test -f to succeed. Show the complete draft, exact target path, and whether the operation will create or replace the file. Ask the user to confirm that exact write. Do not invoke Write, Edit, Bash redirection, or any other mutating tool before an affirmative response.
After confirmation, repeat the link and regular-file checks immediately before writing. Abort if the target changed or cannot be verified safely. Otherwise write only the approved Markdown to the approved repo-local path, read it back, and report success. Never modify another file, hide or ignore the handoff, commit it, or perform an implicit write. If confirmation is declined, return the draft in chat only.
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.
- 2mo ago First seen · 36 lines · 59 tokens per session scan A c855733398a1
handoff is a skill published in the GitHub repository caiowilson/MCP-memento (11 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 501 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 2026-08-30.
Other skills, from other repositories
solr-semantic-search
To build Solr phrase-tagging semantic search: concept tagging, taxonomy, graph paths.
enzyme-sqlite-source
Connect an unfamiliar SQLite database to Enzyme without changing the source data. Inspect the database, decide which query columns represent identity, people, time, content, and folders, show real examples for approval, save a workspace program in the Enzyme language, and verify init and refresh. Use for email…
enzyme-workspace-setup
Set up or check Enzyme in a Markdown workspace. Use for first setup, re-setup, diagnosis, or requested cleanup; existing Enzyme files do not prove setup is complete. Write settings from the user's own map of their notes, review them with the user, demonstrate an answer from real notes, and repair only an evidenced…
enzyme
Use Enzyme in an already activated Obsidian, Markdown, or Hermes workspace for working-memory retrieval, source-grounded exploration, search by keyword and meaning, runtime note-writing, and refresh. If the workspace is not initialized, follow the first-time setup section before normal retrieval.
seller-research
Use when researching a merchant, storefront, marketplace seller, or merchant of record for a buying decision, especially when identity, refund terms, fulfillment, counterfeit risk, domain history, or independent buyer outcomes are uncertain.
skills
Your next session starts cold. No memory of what you built, what broke, what you decided. Every memory you write is a gift to that future session. The richer the memory, the less time re-learning.