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/abdurrafay2004/handoff/briefnpx skills add AbdurRafay2004/handoff --skill briefgit 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/brief)<a href="https://agentmods.dev/skills/abdurrafay2004/handoff/brief"><img src="https://agentmods.dev/badge/skills/abdurrafay2004/handoff/brief.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 | $0.00043 | $0.01244 |
| Opus 5 | $0.00022 | $0.00622 |
| Sonnet 5 | $0.00009 | $0.00249 |
| Haiku 4.5 | $0.00004 | $0.00124 |
Grade A, and why
brief 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 6d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brief
Part of the Brief phase — see the workflow skill for tiers and sequencing.
Turn an idea into a clear, approved spec through collaborative dialogue. The user speaks as PM/architect (what and why); you interrogate as the senior engineer until the 2–3 decisions that would hurt later are settled — scope, edge cases, failure paths — then STOP. Don't design the universe.
Tier scaling
- T1 (trivial): skip this skill entirely. Just do the task.
- T2 (standard): a few targeted questions in chat, a 3–6 line spec summary, user says "yes, that's what I want." No document needed.
- T3 (risky — money/auth/data/migrations): full interrogation, written spec, explicit approval before planning.
The process
Understand the context first. Check current project state — files, docs,
recent commits, .handoff/ state if present. If a question can be answered
by exploring the codebase, explore the codebase instead of asking.
If that exploration turns broad (vs. a few targeted greps), it's a delegate trigger — ask the user delegate-or-inline first (
delegateskill).
Read the code before you ask. Before asking anything the code could
answer, gather at least one piece of evidence — grep the symbol, read the
file — and cite path:line in the question itself: not "does this touch the
database?" but "orders/service.ts:142 writes to orders directly — new
column there, or a separate table?" Grounded questions get grounded answers.
If you truly find nothing, say what you searched and proceed as greenfield.
Assess scope before refining details. If the request describes multiple independent subsystems ("build a platform with chat, billing, and analytics"), flag it immediately and help decompose into sub-projects: what are the independent pieces, how do they relate, what order? Then brief the first sub-project. Each sub-project gets its own brief → plan → build cycle.
Ask questions one at a time. Multiple questions at once are bewildering. Prefer multiple choice when possible; open-ended is fine too. For each question, provide your recommended answer — the user corrects a recommendation faster than they produce an answer from scratch. Focus on purpose, constraints, success criteria, and what happens when things fail (empty states, bad input, the payment that doesn't go through).
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.
- 6d ago First seen · 108 lines · 43 tokens per session scan A 27386fa1b2df
brief is a skill published in the GitHub repository AbdurRafay2004/handoff (4 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,244 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
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.
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.
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.
building
Implementation skill for writing production code with TDD. Covers the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns. Loaded by component-builder and bug-investigator.
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.