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/darrencroton/ai-agent-coder/handoffnpx skills add darrencroton/ai-agent-coder --skill handoffgit clone --depth 1 https://github.com/darrencroton/ai-agent-coderWrote 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/darrencroton/ai-agent-coder/handoff)<a href="https://agentmods.dev/skills/darrencroton/ai-agent-coder/handoff"><img src="https://agentmods.dev/badge/skills/darrencroton/ai-agent-coder/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 5.1 | $0.00030 | $0.01511 |
| Opus 5 | $0.00015 | $0.00756 |
| Sonnet 5 | $0.00006 | $0.00302 |
| Haiku 4.5 | $0.00003 | $0.00151 |
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 5d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Principles
Preserve momentum — the next agent must know exactly what to do first. Prefer facts over narrative. Separate confirmed facts from assumptions. Record failed attempts so the next agent does not repeat them. Never include secrets or credentials.
Output
Write or update HANDOFF.md in the project root unless the user requests a different file. If it already exists, update in place — keep still-relevant context, remove stale items. Do not commit the handoff unless told or already part of the repo.
Modes
Choose the lightest mode that preserves continuity.
Quick — use when near a hard usage limit. Target: 10–25 lines. Include only: objective, current status, next action, blockers, files touched, critical warnings.
Full — use for complex or multi-step tasks with significant history. Target: 25–100 lines. Use all sections from the template below.
What To Capture
The template below names the structure — objective, task list, status, blockers, files, validation, next action, and so on. Capture facts under whichever heading fits. Beyond that structure, always capture:
- frozen contract, authorized surface, and authorization gate status when the task used implementation-plan or scoped-implementation
- residual findings and post-plan considerations that were intentionally not fixed in the current frozen slice, including why they did not block and what later follow-up should consider
Never:
- chatty narrative or repeated background
- speculative details that do not affect next steps
- secrets or credential values
Plan Workflow Handoff
When all of the following are true, populate Resume Prompt using the full next-chat launcher below — not the generic resume prompt:
- an implementation plan file exists and was the source of the current work
- you just finished implementing one or more slices or a named batch from that plan
- you are stopping at a slice or batch boundary so the user can review before the next session begins (i.e. you are not running all remaining slices autonomously without user checkpoints)
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.
- 5d ago First seen · 173 lines · 30 tokens per session scan A 39b082685344
handoff is a skill published in the GitHub repository darrencroton/ai-agent-coder (2 stars, last pushed 3d ago), licensed MIT. It adds 30 tokens to every session and 1,511 once invoked, about $0.0002 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…