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 n24q02m/mnemo-mcp --skill session-handoffgit clone --depth 1 https://github.com/n24q02m/mnemo-mcpWrote 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/n24q02m/mnemo-mcp/session-handoff)<a href="https://agentmods.dev/skills/n24q02m/mnemo-mcp/session-handoff"><img src="https://agentmods.dev/badge/skills/n24q02m/mnemo-mcp/session-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/n24q02m/mnemo-mcp/session-handoff"><img src="https://agentmods.dev/badge/skills/n24q02m/mnemo-mcp/session-handoff.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 | $0.00020 | $0.00820 |
| Opus 5 | $0.00010 | $0.00410 |
| Sonnet 5 | $0.00004 | $0.00164 |
| Haiku 4.5 | $0.00002 | $0.00082 |
Grade A, and why
session-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 8d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- session-handoff — 100% identical, 0 lines differ
- session-handoff — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Handoff
Structured end-of-session capture that ensures the NEXT session starts with full context. Enforces "WHY not just WHAT" — every memory must include the reasoning, not just the fact.
Checklist (go through ALL categories)
Before storing anything, review the conversation for each category:
-
Decisions made: Technical choices, architecture decisions, tool selections
- BAD: "Using PostgreSQL"
- GOOD: "Using PostgreSQL over SQLite because we need concurrent writes from multiple workers and the data exceeds 10GB"
-
Preferences expressed: User's workflow preferences, style choices, communication preferences
- BAD: "Prefers short commits"
- GOOD: "Prefers atomic commits (one logical change per commit) because they review PRs commit-by-commit and need clean bisect history"
-
Corrections given: Things the user corrected — these are HIGH PRIORITY (prevents repeat mistakes)
- BAD: "Don't use fmt.Println"
- GOOD: "Corrected: use log.Printf not fmt.Println in Go services because stdout is not captured by the log aggregator (Alloy)"
-
Conventions established: Naming patterns, file organization, coding standards
- BAD: "Use snake_case"
- GOOD: "Convention: snake_case for Python files and functions, but PascalCase for Pydantic models. Established because the codebase mixes both and this was the cleanup decision"
-
Open questions: Unresolved items that need future attention
- Store these explicitly so the next session can address them
- Include what was already tried or considered
Storage Process
For each item identified above:
-
Store with context using
memory(action="add", ...):- Content MUST include WHY, not just WHAT
- Tag with category:
decision,preference,correction,convention,open-question - Tag with project name for scoped retrieval
- Include date context if time-sensitive
-
Verify retrieval (mandatory — do NOT skip):
memory(action="search", query="[natural terms someone would use to find this]")- If the memory does not appear in top results, either:
- Rewrite content with better keywords
- Add more specific tags
- A memory that cannot be found is worthless
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.
- 8d ago First seen · 80 lines · 20 tokens per session scan A 84eb045ad341
session-handoff is a skill published in the GitHub repository n24q02m/mnemo-mcp (10 stars, last pushed today), licensed Apache-2.0. It adds 20 tokens to every session and 820 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 2026-08-31.
Other skills, from other repositories
scrape-batch
Extract many known URLs in one polite, rate-limited pass. Use when the user hands over a list of links, a set of search hits to read in full, or asks to "scrape these pages" / "pull the content from all of them". Drives extract(action="batch"), which fans out with per-domain rate limiting and returns partial results…
compare
Structured comparison of 2+ alternatives with consistent criteria and decision matrix.
research-topic
Multi-step research orchestration. Use when user asks "research X", "summarize current state of Y", "what's the latest on Z", or compares approaches. Calls extract(action="agent") which searches the web, extracts top results, then synthesises a citation-preserving Markdown answer with one configured LLM.
fact-check
Verify a claim using adversarial search — find both supporting AND contradicting evidence.
lock-project-stack
Detect a project's manifest (pyproject.toml / package.json / go.mod / Cargo.toml), pin its library set into wet-mcp's Cabinets projectcontext, then route subsequent docs queries to the locked versions automatically.
add-mechanic
Add game mechanics with correct GDScript 4.x patterns -- movement, health, inventory, save/load.