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/zookanalytics/gc-toolkit/handoffnpx skills add zookanalytics/gc-toolkit --skill handoffgit clone --depth 1 https://github.com/zookanalytics/gc-toolkitWhat 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 | $0.00064 | $0.01540 |
| Opus 5 | $0.00032 | $0.00770 |
| Sonnet 5 | $0.00013 | $0.00308 |
| Haiku 4.5 | $0.00006 | $0.00154 |
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.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Operator-initiated only. Do not invoke this skill without the operator asking for it. If you believe a handoff would help, raise the suggestion in conversation and let the operator decide.
Detect the session shape
This skill has one shape. Confirm you are in it by reading $GC_TEMPLATE:
- Canonical path — controller-restartable named sessions: the
always-on coordination agents in this city (mechanik, deacon, witness).
Their
mode = "always"declaration lets the controller stop and restart them cleanly whengc handofffires. The transcript is replaced; durable state (beads, mail, work) survives.
If $GC_TEMPLATE falls outside that shape — a mode = "on_demand"
session, or anything else — stop and confirm before proceeding.
gc handoff will write the mail but cannot restart the user-attended
process, so the next-life context is delayed until the operator manually
restarts it. Surface the difference and let the operator decide.
If the operator wants a no-questions-asked close — no inventory, no
carry-forward — that is the bye shell helper (! bye), not this skill.
What's being preserved
Conversational state, not work. Assigned beads, inbox mail, dispatched polecats, and durable bead-store records are picked up automatically by the next-life agent's startup checks. What disappears is the active discussion: what the operator and agent were mid-thread on. If it lives only in the transcript, it dies unless the handoff carries it.
The vehicle is the HANDOFF mail: the controller replaces the transcript and the next-life agent reads that mail on its first action. Anything not mentioned in the handoff body is intentionally forgotten.
When the operator asks for it
Recognize as triggers: "handoff", "fresh context" / "reset context" / "clean slate", "wrap this up and reset", "restart [mechanik/deacon] with a clean transcript". Ambiguous phrasings ("let's wrap up" alone) get clarified first: "Do you want a handoff (fresh transcript) or just a summary in place?"
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 · 158 lines · 64 tokens per session scan A 5f6e225ef0c4
handoff is a skill published in the GitHub repository zookanalytics/gc-toolkit (5 stars, last pushed 4d ago), licensed MIT. It adds 64 tokens to every session and 1,540 once invoked, about $0.0003 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
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
hedging-strategy
Hedging strategy design (beta hedge / option protection / tail risk / cross-asset hedging), including hedge-ratio calculation and cost evaluation.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…
oma-hwp
Convert HWP / HWPX / HWPML files to Markdown using kordoc. Extracts text, headings, tables, lists, images, footnotes, and hyperlinks. Use for Korean word processor files (Hangul), government documents, and AI-ready data preparation.
error-recovery
Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure.