Borrowing it
Nothing to install: this file belongs to egregore-labs/egregore. 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/egregore-labs/egregore/main/.claude/skills/handoff/SKILL.mdgit clone --depth 1 https://github.com/egregore-labs/egregoreWrote 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/egregore-labs/egregore/handoff)<a href="https://agentmods.dev/skills/egregore-labs/egregore/handoff"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/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/egregore-labs/egregore/handoff"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 35 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
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 | $0.00054 | $0.05973 |
| Opus 5 | $0.00027 | $0.02986 |
| Sonnet 5 | $0.00011 | $0.01195 |
| Haiku 4.5 | $0.00005 | $0.00597 |
Grade B, and why
handoff scanned grade B with 1 finding 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 10d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
**Local mode** (`mode === "local"`): graph queries and DM-style notifications are unavailable. A recipient-less group notification can be proposed when `telegram_chat_id` is set, but an addressed DM never falls back to t How it starts
The opening of the file, as written. The whole thing — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Address the current session context to a teammate or future you. /handoff is
pure capture; pending-work triage belongs to /activity.
Topic: $ARGUMENTS
Auto-saves. No need to run /save after.
When to invoke
User says: "leave a handoff", "pass this to [name]", "hand off to [name]"
Not this: personal session closure → /wrap · pending handoffs → /activity · push and keep working → /save
Scope: /handoff is the team session-handoff — internal recap addressed to a teammate or future-you, indexed in Neo4j, written to memory/handoffs/, and auto-PR'd to the configured base branch. It may prepare an external notification, but that notification is a separate human-approved action. It is NOT a portable capsule.
Portable, executable capsules — the kind you share with someone outside the team via an egregore.xyz/emissary/e/<id> link — live in /emissary. If the user pastes such a link, asks to "make/send/run an emissary", or wants capsule lifecycle (receive, reply, run), route to /emissary and stop. Do not handle capsules here.
Disambiguation
- "Show me my handoffs" → team handoffs (
/activity). For capsules sent externally, that's/emissaryterritory. - "I'm done", "wrap this up" →
/wrap. - "hand off to alice",
/handoff <topic>→ AUTHOR flow below. - "Let's make an emissary", "send an emissary to alice", pasted
egregore.xyz/emissary/e/<id>→/emissary.
Mode detection
MODE=$(jq -r '.mode // "connected"' egregore.json 2>/dev/null)
Local mode (mode === "local"): graph queries and DM-style notifications are unavailable. A recipient-less group notification can be proposed when telegram_chat_id is set, but an addressed DM never falls back to the group. Nothing is uploaded and there is no shareable URL — the handoff is written to memory/handoffs/ and stays there. Without an org API key the only publishing route is a public, unauthenticated relay (anyone with the link can read it, 7-day TTL), and that is off unless the instance ran bin/settings.sh relay on. Never tell the user their handoff was published when publishStatus is relay-off.
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.
- 10d ago First seen · 403 lines · 54 tokens per session scan B af78aec221ab
handoff is a skill published in the GitHub repository egregore-labs/egregore (289 stars, last pushed 6d ago), licensed MIT. It adds 54 tokens to every session and 5,973 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".
done
Close an increment: ledger check, specweave verify, optional review, then specweave complete. Use when all tasks are done and saying "close increment", "we are done", or "finish up".
xiaohongshu-image-creator
An image-making assistant for Xiaohongshu, a Chinese social platform for lifestyle, product, and educational posts. It creates vertical covers and supporting images matched to the post’s topic, audience, and visual style.
atomic-tdd
Test-first discipline. Auto-triggers on "let's implement X", "add feature Y", "fix bug Z", "write a test for", "implement", "build out", and similar pre-code-change phrases. Iron rule: failing test exists before production code. Skip only for pure docs/config changes with an explicit "skipped because:" note. Explicit…