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 wan-huiyan/context-baton --skill session-handoffgit clone --depth 1 https://github.com/wan-huiyan/context-batonWrote 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/wan-huiyan/context-baton/session-handoff)<a href="https://agentmods.dev/skills/wan-huiyan/context-baton/session-handoff"><img src="https://agentmods.dev/badge/skills/wan-huiyan/context-baton/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/wan-huiyan/context-baton/session-handoff"><img src="https://agentmods.dev/badge/skills/wan-huiyan/context-baton/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 | $0.00247 | $0.08091 |
| Opus 5.5 | $0.00099 | $0.03236 |
| Sonnet 5.5 | $0.00049 | $0.01618 |
| Haiku 4.5 | $0.00025 | $0.00809 |
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 1mo 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 — 633 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Handoff v1.9 — Bucket-aware + reverse-lint + skill-freshness + issue emission
Comprehensive end-of-session knowledge capture with built-in cross-session consolidation. Ensures nothing is lost between sessions and produces a single source of truth when multiple handoffs accumulate.
v1.9 alignment with memory-hygiene v3.3: session output is dispatched across
the canonical 7-bucket docs/ taxonomy — not just docs/handoffs/. At the end of
the workflow, invokes doc-freshness-reverse-lint and a skill-freshness audit
against any memory or SKILL.md files touched this session to surface stale normative
guidance, and emits the future-to-do plan's follow-up items as GitHub issues so
nothing relies on a future session re-reading the handoff to act on them.
Counterpart skill: memory-hygiene v3.3 cleans Claude's persistent memory +
audits project docs/ against the same taxonomy. Run memory-hygiene after
10+ sessions or when docs/ has drifted.
When to use
- End of any non-trivial work session (3+ tasks completed)
- User says "wrap up", "hand over", "create handoff", or similar
- Before context window approaches limits
- After parallel sessions complete and you need one "start here" document
- User says "consolidate", "what's the current state"
Canonical 7-bucket docs/ taxonomy (from memory-hygiene v3.3)
Session output is dispatched to the right bucket — not dumped into one handoff file. A typical rich session produces artifacts in 3-5 of these 7 buckets simultaneously.
| # | Bucket | Write here when the session produced... | Filename convention |
|---|---|---|---|
| 1 | docs/decisions/ |
An architectural / methodological choice worth preserving (go/no-go, tradeoff, supersession) | NNNN-kebab-case.md (ADR — check for duplicate numbers first) |
| 2 | docs/runbooks/ |
A new rerun / retrain / operational procedure, or updated steps to an existing one | <verb>_<noun>.md (e.g. retrain_propensity.md, rerun_guide.md) |
| 3 | docs/analysis/ |
Findings, investigations, diagnostics, discovery write-ups, exploratory analyses | analysis_<topic>.md, discovery_<topic>.md, findings_<topic>.md |
| 4 | docs/references/ |
New/updated schema, data dictionary, API ref, project-convention doc | <system>_reference.md, data_dictionary.md, <topic>_dictionary.md |
| 5 | docs/reviews/ |
Review-panel output, peer review, audit report | review_<topic>.md, <topic>_audit_report.md, next_stage_<topic>.md |
| 6 | docs/handoffs/ |
Always — this session's handoff doc + next-session prompt + (optional) parallel prompts | session_N_handoff.md, session_N+1_prompt.md, session_N+1b_<topic>_prompt.md |
| 7 | docs/deliverables/ |
External-facing artifact (client draft, published output, slide deck, PDF, XLSX) | Keep original extension; add a .provenance.md sibling if the artifact was generated |
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.
- 1mo ago First seen · 633 lines · 247 tokens per session scan A cc78bcd28004
session-handoff is a skill published in the GitHub repository wan-huiyan/context-baton (1 stars, last pushed 3mo ago), licensed MIT. It adds 247 tokens to every session and 8,091 once invoked, about $0.0010 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
ecosystem-audit
ALWAYS use this skill when the user asks any question about their Claude Code setup, installed skills, memory system, lessons, feedbacks, handoffs, worktrees, ADRs, docs, or /.claude directory health. This is the go-to skill for introspection of the Claude Code environment itself. Specifically trigger on: (1) Skill…
llm-wiki
Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings. Ingest sources into linked Markdown, answer questions with citations, lint or upgrade a wiki, and preserve useful synthesis across sessions and agents. Also capture verified task experience, consolidate…
resume
Write down where this stretch of work stopped, so the next session continues instead of restarting. Use at the end of a working session, or when handing the repository to someone else.
reflect
Per-project self-improvement - reads the .harness ledger and feedback memories, then proposes gated rule/threshold/ADR changes so the project stops repeating mistakes. Run periodically.
remember
Review auto-memory entries and propose promotions to CLAUDE.md, CLAUDE.local.md, or shared memory. Also detects outdated, conflicting, and duplicate entries across memory layers.
consolidate
Periodically merge the memory index, long-tier memory files, and the habit file — deduplicate, resolve contradictions to the current truth, absolutize dates, bring HABITS.md back under budget — and propose the result for your confirmation before any write. Use when MEMORY.md grows large (120+ lines), when the habit…