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 AbdurRafay2004/handoff --skill plangit clone --depth 1 https://github.com/AbdurRafay2004/handoffWrote 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/abdurrafay2004/handoff/plan)<a href="https://agentmods.dev/skills/abdurrafay2004/handoff/plan"><img src="https://agentmods.dev/badge/skills/abdurrafay2004/handoff/plan/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/abdurrafay2004/handoff/plan"><img src="https://agentmods.dev/badge/skills/abdurrafay2004/handoff/plan.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 | $0.00042 | $0.01425 |
| Opus 5.5 | $0.00017 | $0.00570 |
| Sonnet 5.5 | $0.00008 | $0.00285 |
| Haiku 4.5 | $0.00004 | $0.00143 |
Grade A, and why
plan 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 15d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan
Part of the Plan phase — see the workflow skill for tiers and sequencing.
Write implementation plans assuming the implementer has zero context for this codebase and questionable taste. Document everything they need: which files to touch per task, the code itself, how to test it, what to check. Bite-sized tasks. DRY. YAGNI. Test-first where the tier demands it. Frequent commits.
Tier scaling
- T1: skip this skill — no plan, just do the task.
- T2: short plan as bullets in chat — files to touch, order of work, verification step. Include the scope summary for the workflow's single combined brief/plan review. No document or separate second approval.
- T3: written plan file the user approves BEFORE build starts. Trade-offs
stated in plain product language. Save to
docs/plans/YYYY-MM-DD-<feature>.md(user preferences override).
Step 0 — challenge the premise
Before planning the how, spend a paragraph on the whether. Is this the right problem at all, or a proxy for a simpler outcome — and what actually breaks if we do nothing? Does existing code already solve part of it? Map each sub-problem to what exists before planning anything parallel. Then name the 10x version of the ask — what would deliver 10x the value for 2x the effort? Usually you still plan the ask, but naming the bigger and the do-nothing versions lets the user pick scope deliberately, not by default.
Scope check
If the spec covers multiple independent subsystems, it should have been
decomposed during brief. If it wasn't, stop and suggest one plan per
subsystem — each producing working, testable software on its own.
File structure first
Before defining tasks, map which files will be created or modified and what each is responsible for. This locks in decomposition decisions.
- Each file gets one clear responsibility, with well-defined interfaces.
- Prefer smaller focused files; edits are more reliable when a file can be held in context at once.
- Files that change together live together — split by responsibility, not by technical layer.
- In existing codebases follow established patterns; if a file you're modifying has grown unwieldy, a split may be part of the plan.
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.
- 15d ago Changed · +1 lines 4354881dc4d0
- 1mo ago First seen · 143 lines · 42 tokens per session scan A 870a425bb44c
plan is a skill published in the GitHub repository AbdurRafay2004/handoff (4 stars, last pushed 10d ago), licensed MIT. It adds 42 tokens to every session and 1,425 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 2026-08-31.
Other skills, from other repositories
checkpoint
Write the current working state (task, decisions, files touched, open problems, next steps) to .amber/STATE.md so it survives compaction and session restarts. Use when the user asks to checkpoint/save state, before risky long operations, when context feels heavy, or before ending a work session.
focus
Declare a focus contract for the current task to keep context lean — scopes which files/dirs are in play, bans out-of-scope exploration, and routes broad searches to subagents. Use when starting a task, when the user says "focus on X", or when the session is drifting across unrelated parts of the codebase.
diet
Audit what is eating the context window in this project (CLAUDE.md size, MCP servers, rules that should be skills) and produce a concrete slimming plan with estimated token savings. Use when the user complains about context filling up fast, frequent compaction, or asks to optimize/reduce context usage.
resume
Reload saved working state from .amber/ (STATE.md, FOCUS.md, checkpoint.md) and continue the previous task. Use when the user says resume/continue where we left off, or at the start of a session in a project that has an .amber directory.
memory-and-handoff
Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.
building
Use when writing production code test-first: the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns.