Borrowing it
Nothing to install: this file belongs to beeltec/context-usage-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/beeltec/context-usage-mcp/main/.agents/skills/handoff/SKILL.mdgit clone --depth 1 https://github.com/beeltec/context-usage-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/beeltec/context-usage-mcp/handoff)<a href="https://agentmods.dev/skills/beeltec/context-usage-mcp/handoff"><img src="https://agentmods.dev/badge/skills/beeltec/context-usage-mcp/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/beeltec/context-usage-mcp/handoff"><img src="https://agentmods.dev/badge/skills/beeltec/context-usage-mcp/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 | $0.00046 | $0.00305 |
| Opus 5.5 | $0.00018 | $0.00122 |
| Sonnet 5.5 | $0.00009 | $0.00061 |
| Haiku 4.5 | $0.00005 | $0.00030 |
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 one self-contained handoff that lets another agent continue without asking the user to repeat context.
- Stop task work and resolve the project root with
git rev-parse --show-toplevel, falling back to the current directory outside Git. - Inspect the conversation, applicable agent instructions, branch,
git status, relevant diffs, changed files, and validation results. - Create
<project-root>/docs/handoffs/and a uniquehandoff-YYYYMMDD-HHMMSS.md; never overwrite another handoff. - Record the timestamp, project root, branch, objective, original requirements, completed and partial work, exact stopping point, workspace state, decisions and rationale, validation, blockers, failed approaches, ordered next steps, first concrete action, and key files. Mark empty sections
None. - Exclude secrets, environment dumps, and unrelated conversation. Do not commit this temporary file unless asked.
- Read the file back and verify that it is non-empty, accurate, and names the next action.
After success, present the repository-relative path followed by this exact prompt with the path substituted:
Continue the work from <repository-relative handoff path>
Do not continue the underlying task after presenting the prompt.
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.
- 2mo ago First seen · 17 lines · 46 tokens per session scan A 47c6ef70c4e3
handoff is a skill published in the GitHub repository beeltec/context-usage-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 305 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
disk-cleanup
Use when the Mac is low on disk or before a build/release/large-media job, to find where space went and reclaim it safely in tiers. Triggers on "disk is full", "free up space", "out of disk", low-free-space warnings, or at session start before heavy work. Measures first, then deletes only regenerable/settled pools…
compact-now
Operator-triggered proactive compaction — Chrono externalizes load-bearing state (active decisions, open tasks, next action) to a snapshot + a durable Vault learning note before invoking Claude Code's native /compact, then resumes from the snapshot. Use when the operator says "/compact-now" / "compact now" or when…
email-formatting
Markdown formatting conventions for email summary documents — heading depth, list style, line length, emoji policy, and a mandatory provenance footer. Read this when producing a markdown report that summarizes one or more email messages so the output matches the project's house style.
json-schema-emails
Canonical shape of the .workflow/emails/emails.json file passed between the fetch and summarize states — required fields (sender, recipient, subject, date, body), types, and field semantics. Read this whenever you write or read emails.json so producer and consumer agree on the shape.
mcptoon
Compress MCP tool discovery with the mcptoon CLI. Trigger when a session has a large MCP tool catalog (many servers/tools), when the user mentions token cost, tool discovery, mcptoon, or asks to list/call MCP tools efficiently. Also route here when the user says the MCP tool list is too large, the agent context window…
cortex-profile
View and manage your cognitive profile — how you think, work patterns, blind spots, and cross-domain connections. Use when the user says 'show my profile', 'how do I work', 'what are my patterns', 'cognitive style', 'blind spots', 'methodology', or at the start of a session to load context. Also use 'rebuild profile'…