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 samuelgudi/iknowkungfu --skill session-handoffgit clone --depth 1 https://github.com/samuelgudi/iknowkungfuWrote 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/samuelgudi/iknowkungfu/session-handoff)<a href="https://agentmods.dev/skills/samuelgudi/iknowkungfu/session-handoff"><img src="https://agentmods.dev/badge/skills/samuelgudi/iknowkungfu/session-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/samuelgudi/iknowkungfu/session-handoff"><img src="https://agentmods.dev/badge/skills/samuelgudi/iknowkungfu/session-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 | $0.00060 | $0.01198 |
| Opus 5 | $0.00030 | $0.00599 |
| Sonnet 5 | $0.00012 | $0.00240 |
| Haiku 4.5 | $0.00006 | $0.00120 |
Grade A, and why
session-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 12d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
session-handoff
A handoff is a document the next session reads to resume work without re-deriving everything from scratch. It is written for a reader with zero prior context — no memory of the conversation, no idea what was tried and rejected, no implicit knowledge of why the current state looks the way it does.
The failure mode this skill prevents: a session ends (context exhausted, or stopped mid-task), the next session opens, and the first twenty minutes are spent reconstructing what the previous session already knew.
Use this skill when
- The session's context window is filling up and the task is not finished.
- A task is being stopped mid-flight and someone (or a future session) will pick it up later.
- Someone explicitly asks for a handoff, a "save state", or a "pick up where we left off" note.
Handoff vs. wrap-up
These are different documents — do not conflate them.
| Handoff | Wrap-up | |
|---|---|---|
| Purpose | Resume unfinished work | Record finished work |
| Audience | The next working session | The project record / your future self |
| Trigger | Context pressure, mid-task stop | Task complete |
| Includes commits/pushes? | No — work is still in progress | Yes — that is the point |
| Lifespan | Discarded once the work resumes | Permanent |
If the work is done, you want a wrap-up (commit, changelog entry, close the issue). If the work is not done, you want a handoff. This skill is about the handoff.
What to capture
A good handoff has exactly five things. More than this is noise; less than this forces re-derivation.
- State — one or two sentences: what was being done, and how far along it is. The orientation line.
- Decisions — every non-obvious choice made and the reason for it. Without the reason, the next session cannot tell a deliberate decision from an accident, and will "fix" things that were intentional.
- In-progress work — what was mid-change when the session stopped, and the exact resume point: the file and line, the half-applied edit, the command that was about to run. "Continue the refactor" is not a resume point. "
src/auth/session.ts:80—validateTokenis extracted but its three callers still call the old inline version" is. - Next steps — the remaining work, ordered by priority, each one a concrete actionable instruction — not a topic.
- Critical context — the things that, if the next session does not know them, will cause a wrong turn: a constraint discovered the hard way, a gotcha, a dead end already explored, an explicit instruction from the user that must be respected. Only things that change behaviour. If it would not change what the next session does, leave it out.
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.
- 12d ago First seen · 81 lines · 60 tokens per session scan A cc58364b273e
session-handoff is a skill published in the GitHub repository samuelgudi/iknowkungfu (2 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,198 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…