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 agentmods add skills/beeltec/context-usage-mcp/handoffnpx skills add beeltec/context-usage-mcp --skill handoffgit clone --depth 1 https://github.com/beeltec/context-usage-mcpWhat 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 | $0.00046 | $0.00305 |
| Opus 5 | $0.00023 | $0.00152 |
| Sonnet 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 2d 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.
- 2d 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 1mo ago), licensed MIT. It adds 46 tokens to every session and 305 once invoked, about $0.0002 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
excel-cli
Excel CLI automation skill for Windows workbooks. Use when a coding agent needs token-efficient, scriptable, or unattended Excel automation via excelcli commands. Best for CI/CD, scheduled jobs, batch processing, PowerShell workflows, and bulk workbook edits. Supports Power Query, DAX, PivotTables, Tables, Ranges…
cortex-setup-project
Bootstrap Cortex for a new project or import existing session history. Use when the user says 'set up Cortex', 'seed this project', 'import my history', 'backfill memories', 'bootstrap memory', 'initialize Cortex for this project', or when starting to use Cortex on an existing codebase that already has Claude Code…
bulk-update
Update properties or content across many pages in a Notion database with dry-run and error recovery.
linkding
Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.
sonarr
This skill should be used when managing TV shows in Sonarr. Use when the user asks to "add a TV show", "search Sonarr", "find a series", "add to Sonarr", "remove a show", "check if show exists", "Sonarr library", "TVDB lookup", or mentions TV show management or Sonarr operations.
delx-wellness-daily-operator
Run the Delx Wellness daily operator loop for Hermes users.