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 alphaelements/handoff-mcp --skill handoff-docsgit clone --depth 1 https://github.com/alphaelements/handoff-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/alphaelements/handoff-mcp/handoff-docs)<a href="https://agentmods.dev/skills/alphaelements/handoff-mcp/handoff-docs"><img src="https://agentmods.dev/badge/skills/alphaelements/handoff-mcp/handoff-docs/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/alphaelements/handoff-mcp/handoff-docs"><img src="https://agentmods.dev/badge/skills/alphaelements/handoff-mcp/handoff-docs.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 | $0.00152 | $0.02960 |
| Opus 5.5 | $0.00061 | $0.01184 |
| Sonnet 5.5 | $0.00030 | $0.00592 |
| Haiku 4.5 | $0.00015 | $0.00296 |
Grade A, and why
handoff-docs 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 3d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff Docs Skill
Structured project documents under .handoff/docs/: one Markdown file per
document, indexed by section, searchable, linked to tasks and to each other.
- Per-tool parameters: references/doc-tools.md
- Section verification matrix and
doc_req_*requirements: references/verification-matrix.md - V-model layer documents (requirements → specs → tests with coverage,
suspects, approval): the
handoff-traceskill (overview, setup) and thehandoff-requirementsskill (how to write items)
When to use
- The user asks to save a spec, design, plan, ADR, guide or note so it survives across sessions — or you write one during development
- Importing an existing directory of Markdown (
specs/,docs/) at once - Reading one section of a large document without loading all of it
- Following how documents relate (parent/child, "implements", "supersedes")
- Linking a document to tasks so it surfaces while those tasks are worked on
A short standalone lesson/rule/gotcha (under a page, no sections) belongs in
project memory instead — see the handoff-memory skill and "Memory vs
Documents" below.
Choose a tracking style first
| you need | use |
|---|---|
| keep a document, read and search it | plain document (doc_save) |
| tick off sections of a spec as implemented | section matrix (doc_verify, see verification-matrix.md) |
| a list of individually tracked requirements from a requirement table | section matrix + doc_req_import (verification-matrix.md) |
| requirements linked to specs and tests, coverage, change impact (suspects), approval | V-model layer document — doc_save(layer=...), see handoff-trace |
A layer document's items come from its body headings; the section matrix's
add_item / set_priority / set_refs(test_refs) and doc_req_import are
refused on it. Pick one style per document.
If the project uses the V-model ([trace] profile is set — check
handoff_get_config), save specs and designs with a layer, or enable
[trace] auto_layer so doc_save infers one: spec → requirement,
design → detailed_spec, plan → detailed_spec (override with
[trace] plan_default_layer); adr / guide / note never get one. An
explicit layer always wins ("" clears it and suppresses inference for that
call). For layers the table does not cover (basic_spec, acceptance, …),
always pass layer explicitly.
What ships with it
3 files 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.
- 3d ago Changed · -646 lines 39ffe9a86ffe
- 7d ago Changed · +55 lines · +27 tokens per session 98fb47862e45
- 10d ago Changed · +47 lines 69d43ae609be
- 14d ago Changed · +55 lines 210436dbb444
- 18d ago Changed · +161 lines 690d32c529c7
- 25d ago Changed · +49 lines e33e24e49e7b
- 1mo ago First seen · 485 lines · 125 tokens per session scan A ac057d8b9114
handoff-docs is a skill published in the GitHub repository alphaelements/handoff-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 152 tokens to every session and 2,960 once invoked, about $0.0006 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.