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/jcottam/agent-resources/handoffnpx skills add jcottam/agent-resources --skill handoffgit clone --depth 1 https://github.com/jcottam/agent-resourcesWrote 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/jcottam/agent-resources/handoff)<a href="https://agentmods.dev/skills/jcottam/agent-resources/handoff"><img src="https://agentmods.dev/badge/skills/jcottam/agent-resources/handoff.svg" alt="Measured on agentmods" 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 | $0.00095 | $0.02434 |
| Opus 5 | $0.00048 | $0.01217 |
| Sonnet 5 | $0.00019 | $0.00487 |
| Haiku 4.5 | $0.00010 | $0.00243 |
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 4d 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Editorially compress session context into a small markdown checkpoint an agent can load in a new turn. Raw transcripts live under Cursor project folders; handoffs are curated, short, and decision-dense.
SCRIPTS refers to the scripts/ directory next to this file.
HANDOFFS_ROOT is ~/.agents/handoffs/.
This skill is not the content-wireframe "Handoff" (approved copy → implementer). It is session/task continuity across chats or agents.
Choose mode
| User intent | Mode |
|---|---|
| handoff, compact, checkpoint, save context, done for today | Create |
resume handoff, continue from handoff, load handoff, @ handoff file |
Resume |
If ambiguous, ask once which mode they want.
Create
Phase 0 — Eligibility
Skip creating a handoff (tell the user why) if all are true:
- The task is fully done with nothing left to continue
- There are no decisions, partial state, or open questions worth preserving
- A PR/commit message or one sentence is enough (
shipmay be better)
Phase 1 — Gather inputs
Collect signal in this order. Do not paste tool dumps or transcript chunks into the handoff file.
- User goal and latest instructions
- Next session focus — if the user passed slash/command arguments or stated what the next chat is for, treat that as the primary lens for Next steps and Suggested skills
- Run
$SCRIPTS/workspace-id.shand parse JSON (workspace_path,workspace_id,git_head) - If git repo:
git status -sb,git diff --stat(and branch name) - Files the user
@mentioned or the agent edited this session - Explicit decisions and reversals from the conversation
- Open questions, blockers, and failed approaches (do not redo)
- Existing artifacts — scan for PRDs, specs, plans, ADRs, issues, open PRs, and large on-disk docs. Note paths only; do not copy their contents into the handoff (see deduplication below)
- Session activity — condensed outcomes from tool use this session (files written, commands run and key results, PRs opened, tests pass/fail counts). Outcomes only; no raw stdout or play-by-play
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.
- 4d ago First seen · 293 lines · 95 tokens per session scan A d8bb6b94c13a
handoff is a skill published in the GitHub repository jcottam/agent-resources (30 stars, last pushed 28d ago), licensed MIT. It adds 95 tokens to every session and 2,434 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
update-knowledge-base
Analyze code changes and update KNOWLEDGEBASE.md with architectural and feature changes.
deep-clean
Full-spectrum consolidation of AI agent configuration files. Goes beyond memory-only dream skills: audits and optimizes context files (AGENTS.md/AGENTS.md/GEMINI.md/.cursorrules), rules, skills, and memory. Detects stale references, dead file paths, duplicated rules, stack mismatches, contradictions, vague directives…
caveman-compress
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or…
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
comet-memory
使用于 Comet 需要根据有界语义评审包判断是否值得保存个人记忆、候选、更新、遗忘或跳过时。.
product-help
Use this skill when the user asks about my own features, configuration, or usage — installation, skills, Web UI, CLI, API config, memory, sessions, encryption, white-label, publishing, pricing, troubleshooting, or restarting the server. Do NOT trigger for general coding tasks unrelated to me.