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 sharpninja/McpServer --skill handoffgit clone --depth 1 https://github.com/sharpninja/McpServerWrote 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/sharpninja/mcpserver/handoff)<a href="https://agentmods.dev/skills/sharpninja/mcpserver/handoff"><img src="https://agentmods.dev/badge/skills/sharpninja/mcpserver/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/sharpninja/mcpserver/handoff"><img src="https://agentmods.dev/badge/skills/sharpninja/mcpserver/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 | $0.00029 | $0.00427 |
| Opus 5.5 | $0.00012 | $0.00171 |
| Sonnet 5.5 | $0.00006 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00043 |
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 19d 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
Handoff Ingestion
Use the shared workflow.handoff.* REPL namespace or native handoff_ingest / handoff_get / handoff_approve tools. Every surface, including this skill's ingest/get/approve workflow, must go through IHandoffIngestionService. Do not create TODOs from parsed AI text yourself.
Do not edit TODO.yaml or handoff run rows directly.
Ingest
method: workflow.handoff.ingest
params:
sourceKind: Path
path: docs/handoffs/example.md
mode: DraftOnly
sourceKind is Path, Content, or Artifact. mode is DraftOnly (default), RequireReview, or CreateWhenConfident.
DraftOnly never mutates TODO state. RequireReview stores an approvable run. CreateWhenConfident creates a TODO only when confidence is at least 0.75 and no error diagnostic exists.
Inspect
method: workflow.handoff.get
params:
runId: handoff-run-001
Approve
method: workflow.handoff.approve
params:
runId: handoff-run-001
approved: true
reviewer: operator
Approval revalidates the stored draft before calling the TODO service. ID collisions are never silently renamed.
YAML Mutation Rule
When YAML must be changed, deserialize the complete document into an object, mutate the object, serialize the object, and save the result. Do not append YAML snippets, replace YAML lines, remove YAML lines, or build YAML payloads as strings. For PowerShell work, use plugins/core/lib-ps/yaml-object-mutation.ps1 and call Set-McpYamlObjectValue or Update-McpYamlObject.
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.
- 19d ago Changed · +4 lines c475040b4924
- 1mo ago First seen · 46 lines · 29 tokens per session scan A b8ac51fdcca1
handoff is a skill published in the GitHub repository sharpninja/McpServer (4 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 427 once invoked, about $0.0001 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 2026-09-04.
Other skills, from other repositories
omh-agent-board
This is a Hermes-native agent-board workflow skill.
omh-research-department
This is a Hermes-native research-department workflow skill.
triage-sweep
Backfill labels across oh-my-hermes issues and pull requests. Run manually to sweep everything currently unlabeled, or pass a number to triage one item. Use when issues and PRs have accumulated without labels, after adding a new label to .github/labels.yml, or before a release when the backlog needs to be readable by…
omh-cto-loop
This is an OMH cto-loop workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
internal-comms
Author clear, high-impact internal engineering communications including 3P status updates, blameless incident postmortems, architecture decision memos, and leadership briefs. Use when writing technical updates, sprint reports, incident reviews, or organizational engineering announcements.
work-summary
Generates a project dashboard from MCP work items. Default is a lean, attention-first view: what's in flight, what's blocked, what to do next, what's queued. Use when the user says: project status, what's active, show me the dashboard, work summary, what should I work on, project health, what's blocked, where did I…