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 Rijul1204/rashedul-agentic-engineering --skill handoffgit clone --depth 1 https://github.com/Rijul1204/rashedul-agentic-engineeringWrote 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/rijul1204/rashedul-agentic-engineering/handoff)<a href="https://agentmods.dev/skills/rijul1204/rashedul-agentic-engineering/handoff"><img src="https://agentmods.dev/badge/skills/rijul1204/rashedul-agentic-engineering/handoff.svg" alt="Measured on agentmods" 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 | $0.00142 | $0.03139 |
| Opus 5 | $0.00071 | $0.01570 |
| Sonnet 5 | $0.00028 | $0.00628 |
| Haiku 4.5 | $0.00014 | $0.00314 |
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 7d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
handoff
Compact the current conversation into a single self-contained Markdown document that a fresh agent can read at the start of the next session and immediately know: what to do, what's already done, what's blocked, and which skills/files to touch. Save it to the OS temp directory (NOT the workspace) so it doesn't accidentally get committed.
The handoff doc is a briefing, not a transcript. It references — never duplicates — content that already lives in other artifacts (PRs, plans, design docs, commits, memory entries, ADRs, issue trackers).
See README.md for the credit (Matt Pocock's original handoff) and install / use instructions.
When to invoke
Fire on any of:
- User invokes
/handoff(optionally with an argument describing the next session's focus). - User says "create a handoff doc", "write a handoff document", "compact this", "pass off to another session", "checkpoint this conversation".
- User says "what will the next session focus on" or "I'll pick this up tomorrow".
- User signals an imminent context-window break and wants the work to survive.
When NOT to invoke
- Mid-task, when the user wants you to keep going. Handoff is a session-boundary ritual, not a status update mid-conversation.
- For one-off questions ("what's the status?") — answer directly; don't write a file.
- When the conversation is short (<20 substantive turns) and nothing material would be lost by starting fresh.
- When the user is asking for documentation that should live IN the repo (design docs, ADRs, READMEs). Handoff docs are ephemeral session-bridge artifacts; if it deserves permanent docs, write it alongside code (e.g. under
docs/,project-management/, orarchitecture/), not in/tmp.
Step 1 — Parse the argument
If the user passed an argument to /handoff (or named the next session's focus in their message), treat it as the mission statement. The whole doc tailors to that mission.
Examples of argument shapes you might see:
What ships with it
1 file 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.
- 7d ago First seen · 233 lines · 142 tokens per session scan A 2dde54847b1a
handoff is a skill published in the GitHub repository Rijul1204/rashedul-agentic-engineering (2 stars, last pushed 1mo ago), licensed MIT. It adds 142 tokens to every session and 3,139 once invoked, about $0.0007 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
conversation-archaeologist
Mine ALL past Claude conversations to build a living 'User Manual About You'. Extract writing style, business context, goals, preferences, and patterns. Make all other skills smarter with context.
agent-memory-mcp
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
magic-compact
Compact this Claude Code session.
skill-status
A study-progress companion that reads a saved JSON file to remember your learning plan, progress, predictions, and past notes between sessions.
second-brain-ingest
Ingests an item (inline text and/or attached on-device files) into the domain-split knowledge wiki. Classifies the item's domain (work | life), critically triages each fact (information vs. bloat → document / one line / nothing), writes a factual source page, copies attached artifacts into raw/assets, re-synthesizes…
second-brain-lint
Scheduled integrity pass over the domain-split knowledge wiki. Runs over work/wiki, life/wiki, and shared/wiki independently and flags: filename != H1, broken [[wikilinks]], orphan pages, strong-index integrity gaps, cross-domain leaks, stray task checkboxes (knowledge-only violations), bloat / fragmentation…