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 will-pagane/claude-superdev-harness --skill session-handoffgit clone --depth 1 https://github.com/will-pagane/claude-superdev-harnessWrote 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/will-pagane/claude-superdev-harness/session-handoff)<a href="https://agentmods.dev/skills/will-pagane/claude-superdev-harness/session-handoff"><img src="https://agentmods.dev/badge/skills/will-pagane/claude-superdev-harness/session-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 | $0.00091 | $0.01236 |
| Opus 5 | $0.00046 | $0.00618 |
| Sonnet 5 | $0.00018 | $0.00247 |
| Haiku 4.5 | $0.00009 | $0.00124 |
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 8d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Handoff
Overview
The next agent has zero memory of this session. The handoff prompt is its only inheritance — it must make that agent fully autonomous from a cold start, built from fresh evidence, not your recollection.
Core principle: brief on the past, complete on the present and the future. The next agent doesn't need a changelog of how we got here — it needs to know exactly what is true now and what to do next.
When to Use
- User asks for a handoff / prompt for the next session / "continuar de onde paramos"
- User invokes
/session-handoff - Context is running low and work must cross a session boundary
Not for: writing project docs, commit messages, or PR descriptions. Those are artifacts about the work; a handoff is an instruction set for the next agent.
The Iron Rule: Evidence Before Writing
Never write the handoff from memory. Your recollection drifts — commit hashes, file names, and "done" status get fabricated. Gather real evidence first, every time, even for a short session.
Run and read the output of:
git -C <repo> status # uncommitted / modified / untracked files — what is NOT saved
git -C <repo> log --oneline -15 # recent commits — confirm hashes & messages, don't guess
git -C <repo> branch --show-current
git -C <repo> diff --stat # scope of uncommitted changes
Then review this conversation for: the goal, decisions made and why, the task in flight, blockers, and open questions. Check any open TODOs (TaskList / TodoWrite state).
If a fact isn't in the evidence or the conversation, do not invent it — either verify it or label it (a confirmar).
Output Contract
- Emit the handoff as ONE fenced code block so the user copies it in a single gesture.
- The block must be self-contained: the next agent needs nothing but the repo + this prompt. No "as discussed", no references to this chat.
- Outside the block: at most one line ("Pronto — é só copiar o bloco abaixo para a próxima sessão.").
- Past = a few sentences. Present + Future = exhaustive.
- State
git/branch facts exactly as the commands returned them.
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.
- 8d ago First seen · 89 lines · 91 tokens per session scan A 7f417aa8474d
session-handoff is a skill published in the GitHub repository will-pagane/claude-superdev-harness (4 stars, last pushed 5d ago), licensed MIT. It adds 91 tokens to every session and 1,236 once invoked, about $0.0005 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
aenv
Use when the user wants to set up, switch between, or manage aenv namespaces — named bundles of CLAUDE.md, skills, MCP entries, and other AI-coding-harness config — in a project OR globally across $HOME. Triggers include aenv … mentioned directly, "switch namespace/profile", "activate/deactivate", "create/snapshot a…
threads
A workflow guide for coordinating several coding agents on a broad task. It defines separate work lanes, file ownership, review gates, and checks that the work is complete.
vscode-doctor
Diagnose slow or freezing VS Code-compatible editors with evidence-first, zero-hardcoded-assumption workflow. Use when the user reports editor lag, typing delay, UI freezes, extension host stalls, file watcher noise, high editor CPU/RSS, uses VS Code/Cursor as a file browser over a large folder, or wants a safe editor…
build-product-demo
Plan, produce, or diagnose evidence-backed product demo videos and screen-recorded promotional walkthroughs. Use when the user asks to make a product demo, launch video, feature showcase, app walkthrough, demo reel, or polished recording; wants every important capability shown without a slow feature tour; asks to…
multi-ai-research
A research workflow that sends one question to several AI systems and internal agents, then compares their findings. It groups results by agreement, disagreement, and confidence.
observability-sre
Observability and SRE expert. Use when setting up monitoring, logging, tracing, defining SLOs, or managing incidents. Covers Prometheus, Grafana, OpenTelemetry, and incident response best practices.