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 kensaurus/cursor-kenji --skill handoffgit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/handoff)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/handoff"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/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/kensaurus/cursor-kenji/handoff"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/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 | $0.00040 | $0.00699 |
| Opus 5.5 | $0.00016 | $0.00280 |
| Sonnet 5.5 | $0.00008 | $0.00140 |
| Haiku 4.5 | $0.00004 | $0.00070 |
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 1mo 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Degree of freedom: LOW. Contents, redaction, and temp-dir save
[LOW freedom — run exactly]. What to emphasize for the next session
[HIGH freedom].
Adapted from mattpocock/skills (MIT).
How to reason
- Observe — what is done, verified, and still open
- Interpret — which claims are implemented vs scoped-verified vs assumed
- Classify — include / point-at-artifact / omit (already in an ADR)
- Severity — a false "green" in the handoff is worse than a missing detail
Worked example
Observe: auth UI landed; RLS migration is a local file only; tests not run. Interpret: UI is implemented, backend is not deployed-verified. Classify: write "implemented, not verified"; point at the migration path; do not say SHIP. Save: OS temp file, print the path; do not commit the handoff into the repo.
Self-critique before writing
- Ladder honest — no upgraded verification claim
- No secrets — keys/tokens/PII redacted
- Pointers not copies — ADRs and plans referenced by path
- Right owner — permanent decisions →
docs-adr, not this file
Write a handoff document summarizing the current conversation so a fresh agent can continue the work. Save it to the OS temporary directory — not the current workspace — and print the path.
Contents
- State: what was attempted, what is done, what is verified vs merely edited.
- Next steps: the concrete remaining work, in order, with file paths.
- Suggested skills: which skills the next agent should invoke, and for what.
- Pointers, not copies: do not duplicate content already captured in other artifacts (specs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.
- Gotchas: anything non-obvious the next agent would otherwise rediscover the hard way (flaky tests, env quirks, decisions already ruled out).
Rules
- Redact sensitive information: API keys, passwords, tokens, PII.
- If the user passed an argument, treat it as the next session's focus and tailor the document accordingly.
- Be honest about verification state — use the ladder from
verification-before-completion: implemented → scoped verified → repository green → PR green → deployed verified. Never upgrade a claim in a handoff. - Permanent decisions (stack, layering, rejected alternatives) belong in
docs-adr, not in the handoff. Point atdocs/adr/INDEX.mdif it exists; do not re-copy those records here.
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.
- 1mo ago Changed · +1 lines 9a3b1c89b20e
- 1mo ago First seen · 66 lines · 40 tokens per session scan A dd0221bf61c9
handoff is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 26d ago), licensed MIT. It adds 40 tokens to every session and 699 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
noteplan
Read, search, create, and edit NotePlan notes and daily logs directly via the filesystem. Use this skill whenever the user references NotePlan, daily notes, weekly notes, project notes, or wants to check/update their planning. Triggers: 'noteplan', 'daily note', 'today's note', 'weekly note', 'check my notes', 'add to…
lno-task-prioritization
Classify tasks as Leverage, Neutral, or Overhead using Shreyas Doshi's LNO framework to maximize impact and reduce stress. Use when the user is planning their week, feeling overwhelmed, prioritizing a to-do list, doing sprint planning, or asking how to spend their time more effectively.
dynamic-context
Use when managing context window to optimize token usage and prevent context bloat.
cursor-delegate
Delegate bounded light-to-medium implementation, investigation, documentation, configuration, testing, and tooling work to Cursor Bridge after the primary agent owns direction and risk boundaries. Also use when the user explicitly asks to create, keep, continue, inspect, or close the same Cursor execution session…
agent-work-receipt
Produces a conservative agent work receipt after completed work: finished output, time estimates, review burden, risks, and value judgment. Use when the user invokes /agent-work-receipt, asks for a work receipt, or wants to measure agent productivity honestly after a session.
hot-reload-optimizer
Optimizes hot module replacement and fast refresh for development speed with Vite, Next.js, and webpack configurations. Use when users request "hot reload", "HMR optimization", "fast refresh", "dev server speed", or "development performance".