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 DollarDill/beads-superpowers --skill session-handoffgit clone --depth 1 https://github.com/DollarDill/beads-superpowersWrote 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/dollardill/beads-superpowers/session-handoff)<a href="https://agentmods.dev/skills/dollardill/beads-superpowers/session-handoff"><img src="https://agentmods.dev/badge/skills/dollardill/beads-superpowers/session-handoff/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/dollardill/beads-superpowers/session-handoff"><img src="https://agentmods.dev/badge/skills/dollardill/beads-superpowers/session-handoff.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 | $0.00047 | $0.01116 |
| Opus 5 | $0.00023 | $0.00558 |
| Sonnet 5 | $0.00009 | $0.00223 |
| Haiku 4.5 | $0.00005 | $0.00112 |
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 9d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Handoff
Write a grounded handoff document — and a one-line continuation memory — so a fresh session can resume exactly where this one left off.
Announce at start: "I'm using the session-handoff skill to write a session handoff."
Human-invoked only. A human fires this skill directly (slash command or explicit ask) — before
/clear,/compact, a context limit, or a teammate handoff. It stays off every agent-trigger surface by design.
When a human uses this
- Before
/clearor/compact, mid-task, when context is about to be lost. - End of a working session, to seed the next one.
- Handing work to a teammate or another agent.
Optional argument: a short description of what the next session will focus on — used to tailor Work In Progress / Loose Threads / Suggested Skills.
Pipeline
- Gather (read-only, run the commands — do not recall):
git status -sb,git log --oneline -15,git diff --stat, branch + ahead/behind;bd ready,bd blocked,bd count --by-status, in-progress beads; list the spec, plan, and architecture-decision-record files touched this session. Done when: every listed command has run and its output is captured. - Synthesize into the bundled template (
handoff-template.md). Reference artifacts by path — never paste their bodies (commits, ADRs, specs, plans, diffs). Duplicating bloats the doc and goes stale. Done when: every section maps to a captured fact, referenced by path. - Write the doc — Default:
.internal/handoff/YYYY-MM-DD[-HHMMSS]-<topic>-handoff.md(-HHMMSSonly if a same-day handoff exists). (The same-day check globs the inbox.internal/handoff/*.mdonly; archived docs underarchive/are out of scope and do not affect same-day naming.) If the human names another location, write there.mkdir -pthe target first. Done when: the doc exists at the target path. - Write the continuation memory —
bd remember "continuation-<date>-<topic>: <one-line pointer to doc path + headline state>"(episodic continuation record; one-line pointer only). Done when:bd rememberhas run for the continuation key. - Verification (externally anchored — output the result block):
- Cross-check each state line against the captured Phase-1 command output.
- Gitignore safety:
git check-ignore <output-path>; if NOT ignored, warn the human ("⚠️ is not gitignored; a handoff can contain sensitive session state") and offer to add it to.gitignorebefore writing. ls <path>confirms the doc exists;bd memories <key>confirms the memory.- Secret-scan grep over the doc (
sk-,ghp_,AKIA,-----BEGIN,password=) — a backstop, not a guarantee. - The narrative synthesis is the author's recollection — not externally verified; that is why it references artifacts by path. Done when: the confirmation block is output — doc path · memory key · gitignore-safety result · secret-scan result.
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.
- 9d ago First seen · 84 lines · 47 tokens per session scan A 56f9818bc885
session-handoff is a skill published in the GitHub repository DollarDill/beads-superpowers (26 stars, last pushed 17d ago), licensed MIT. It adds 47 tokens to every session and 1,116 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 2026-08-30.
Other skills, from other repositories
ucai-patterns
Use when the user asks about Claude Code best practices, how to write agents, how to use hooks, how to manage context, or how to work effectively with Claude Code's native systems.
orient
Use when user invokes /orient with a topic keyword, entity type, project name, time qualifier, or combination. Also triggers on "what do we know about X", "remind me about X", "where did we leave off on X". Provides targeted context loading — searches the MCP Memory Server graph, knowledge files, journal entries, and…
memory
Use when user invokes /memory with a subcommand (search, trace, add, episode, status). Also triggers on "search my memory for X", "add to memory", "what do I know about X" (when membrain is available), "memory status", "memory trace". Searches and manages the membrain knowledge graph via MCP tools or HTTP API.
capture
Use when user invokes /capture to capture information from the current conversation into a staging file for later reflection and knowledge graph processing. Accepts no arguments (auto-extract), specific facts as text, or filter keywords like "decisions" or "technical". Do NOT use when the user wants to write directly…
lembas
Use between workflow phases or when context feels bloated. Writes a structured checkpoint capturing task, findings, files, state, and next steps, then continues from that summary instead of the full history. Invoke standalone or automatically between quest phases.
furl
How the Furl context-compression plugin works in Claude Code and Codex — the furlcompress / furlretrieve / furlstats / furlpurge / furlsearch / furllist MCP tools, the > retrieval flow, and Claude Code's optional automatic hooks. Use when the user asks what Furl is doing, how to compress or retrieve content, why…