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/aethrox/doctrine/handoffnpx skills add aethrox/doctrine --skill handoffgit clone --depth 1 https://github.com/aethrox/doctrineWrote 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/aethrox/doctrine/handoff)<a href="https://agentmods.dev/skills/aethrox/doctrine/handoff"><img src="https://agentmods.dev/badge/skills/aethrox/doctrine/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 | $0.00072 | $0.00794 |
| Opus 5 | $0.00036 | $0.00397 |
| Sonnet 5 | $0.00014 | $0.00159 |
| Haiku 4.5 | $0.00007 | $0.00079 |
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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
A handoff fails when the receiver has to reconstruct context the sender already had. This skill's defining constraint, from SBAR (Situation-Background-Assessment-Recommendation); the structured handoff standard behind the Joint Commission's National Patient Safety Goal for handoff communication, adapted here from clinical and on-call practice: every handoff has exactly four parts, in that order, and nothing that belongs in one part gets buried inside another.
This covers handing off live, in-progress work between owners: an on-call shift, an open incident, or a task mid-flight. It is not the same job as compacting a conversation for a fresh agent session to resume (that's a session-continuity concern) or as writing a postmortem (that's incident-response's closed-incident artifact, written after the fact rather than mid-handoff).
Phase 1: Situation
State the current state in one or two lines: what's happening right now, headline only. A reader who stops after this line should still know whether this is urgent. Don't lead with history or analysis; the situation is the "what," not the "how we got here."
Phase 2: Background
Give only the context that changes what the receiver does next: what's already been tried, what's already been ruled out, what decisions are already made and shouldn't be re-litigated. A background section that restates everything from the start forces the receiver to re-derive what actually matters; the discipline here is inclusion by relevance, not by completeness. If something was tried and failed, say so explicitly; the single most expensive handoff failure is the receiver re-attempting a dead end because nobody mentioned it was already dead.
Phase 3: Assessment
State the current read of the problem, not just facts, but the sender's judgment: how serious is this, what's the actual root concern, what's still genuinely unknown versus just not yet written down. This is the part a bare status report skips, and it's the part that carries the most value, because it's the sender's accumulated judgment, not just a log of events.
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.
- 5d ago First seen · 40 lines · 72 tokens per session scan A 6af743fb425c
handoff is a skill published in the GitHub repository aethrox/doctrine (18 stars, last pushed 24d ago), licensed MIT. It adds 72 tokens to every session and 794 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
openspec-verify-change
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
planning-and-task-breakdown
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.