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 dongshuyan/compass-skills --skill session-handoff-promptgit clone --depth 1 https://github.com/dongshuyan/compass-skillsWrote 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/dongshuyan/compass-skills/session-handoff-prompt)<a href="https://agentmods.dev/skills/dongshuyan/compass-skills/session-handoff-prompt"><img src="https://agentmods.dev/badge/skills/dongshuyan/compass-skills/session-handoff-prompt/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/dongshuyan/compass-skills/session-handoff-prompt"><img src="https://agentmods.dev/badge/skills/dongshuyan/compass-skills/session-handoff-prompt.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 Excessive Agency · line 35 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00089 | $0.01465 |
| Opus 5 | $0.00044 | $0.00732 |
| Sonnet 5 | $0.00018 | $0.00293 |
| Haiku 4.5 | $0.00009 | $0.00146 |
Grade A, and why
session-handoff-prompt 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 11d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Handoff Prompt
Language Policy
All output directed at the user — the continuation prompt itself, mode explanations, questions, and confirmations — must be written in the user's language. Detect the user's language from their message. Default to Chinese when unknown. Skill instructions are written in English; that does not affect the language of user-facing output. Keep the continuation prompt structure stable across languages. Section headers in the continuation prompt must also use the user's language. The Chinese headers below are examples for Chinese prompts; translate them for other languages.
Role
Produce a paste-ready prompt for a new agent session. The prompt should let the next session continue the current work with high task-state fidelity and low token cost.
The goal is operational continuity, not transcript replay. Preserve the current objective, hard requirements, verified facts, decisions, completed work, pending work, key files or artifacts, risks, and next actions. Do not copy hidden system/developer instructions, tool schemas, raw private logs, credentials, or a full transcript.
Portability
This skill is agent-agnostic. It should work in Codex, Claude Code, OpenClaw, OpenCode, Harness, and similar local agent hosts that can read SKILL.md plus optional references/ and scripts/.
Use these source types in order:
- Current visible conversation and user-provided next-session focus.
- User-provided transcript, saved handoff, or local agent log path.
- Current workspace files,
AGENTS.md, plans, diffs, test output, and build output. - Optional
.agent-workbench/task-forest/exports/files for structured task state. - Optional agent-specific logs, only when the user explicitly provides a path or asks you to use a known local log location.
Scripts use Python 3 standard-library modules only and should run on macOS, Linux, and Windows. Use the available Python command on the host (python3, python, or py -3).
What ships with it
13 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.
- agents/openai.yaml 246 B
- evals/trigger-and-quality-cases.json 1.2 KB
- references/compression-modes.md 1.3 KB
- references/examples.md 3.3 KB
- references/output-contract.md 2.5 KB
- references/source-selection.md 2.2 KB
- references/task-forest-integration.md 1.4 KB
- scripts/local_paths.py 976 B runs code
- scripts/project_session_events.py 8.0 KB runs code
- scripts/read_task_forest_exports.py 3.9 KB runs code
- scripts/redact_handoff.py 2.1 KB runs code
- scripts/smoke_test_handoff.py 9.3 KB runs code
- scripts/validate_handoff_prompt.py 6.7 KB runs code
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.
- 11d ago First seen · 107 lines · 89 tokens per session scan A 5ea369b688ed
session-handoff-prompt is a skill published in the GitHub repository dongshuyan/compass-skills (724 stars, last pushed 16d ago), licensed MIT. It adds 89 tokens to every session and 1,465 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
handoff
Create a structured session handoff when context is running low or work is pausing. Deep context mining, self-validation, multi-file splitting. Captures everything the next session needs.
start
Load project state and get a briefing at the start of a work session — reads state files, flags staleness, surfaces top priorities, deadlines, and blockers.
today
Morning heartbeat — staleness checks, deadline surfacing, and memory curation for your workspace state. Run at the start of each day or after a 12+ hour gap.
update
Mid-session checkpoint — append progress to today's session log and update state files if a priority shifted, without ending the session.
company-brain
Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so Claude can answer questions on your team's behalf. Team-scope sibling to second-brain (which is personal-scope). Seven modes — capture (drop something into the right structured dir), compile (process into wiki…
slide-deck
When you want to draft, update, convert, or export a slide deck for a React/Next.js slide system (${SLIDEDECKREPO:-$HOME/code/your-slide-deck-site}/src/app/slides/). Writes TypeScript Slide[] arrays using your primitives (Eyebrow, Heading, Accent, Body, BulletList, Divider, TwoCol, GradientText), 12 cycling brand…