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 hariharapanigrahy/layerkit --skill layerkit-session-handoffgit clone --depth 1 https://github.com/hariharapanigrahy/layerkitWrote 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/hariharapanigrahy/layerkit/layerkit-session-handoff)<a href="https://agentmods.dev/skills/hariharapanigrahy/layerkit/layerkit-session-handoff"><img src="https://agentmods.dev/badge/skills/hariharapanigrahy/layerkit/layerkit-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/hariharapanigrahy/layerkit/layerkit-session-handoff"><img src="https://agentmods.dev/badge/skills/hariharapanigrahy/layerkit/layerkit-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 | $0.00023 | $0.00641 |
| Opus 5.5 | $0.00009 | $0.00256 |
| Sonnet 5.5 | $0.00005 | $0.00128 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
layerkit-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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
layerkit-session-handoff
End-of-session (or mid-pipeline) handoff: durable runbook under memory so another agent continues without re-inventing context.
Protocol
- Gather state:
layerkit repo status
layerkit proposal list
layerkit map list
layerkit agent status
layerkit memory index
layerkit doctor
- Prefer the handoff CLI (template + pipeline status + memory write):
layerkit handoff write \
--vendor <vendor> \
--goal "<one-sentence outcome>" \
--done "research: map validated" \
--done "author: source helper updated" \
--next "layerkit-privacy-review: confirm consent rules" \
--next "layerkit agent mark-done --step privacy --evidence <path>" \
--next "run package verification and checker review" \
--blocked "need live credentials from owner" \
--out memory
Writes {projectDir}/memory/runbooks/handoff-<vendor|project>.md and refreshes memory INDEX.
- Or author manually with required sections:
# Handoff runbook — <vendor or project>
## Goal
## Done
- skills completed, proposal ids, validate status
## In progress
- current skill, open files, partial drafts
## Blocked
- exact residual human questions; who to ask
## Evidence index
- key source URLs + memory paths
## Next 3 actions
1. ...
2. ...
3. ...
## Forbidden
- do not invent; do not apply without checker; do not open deny-paths
## Quality
- last package verification result; coverage if any
## Outcome checkpoints
- what had to pass; proof artifact; fallback if it failed
## Unresolved errors
- exact red gates, failing assertions, or residual risks
Manual persist:
layerkit memory append --type runbooks --title "handoff <vendor>" --vendor <vendor> --body-file ./handoff.md
layerkit memory index
- Point the next agent at:
{projectDir}/memory/INDEX.md+ this runbook +layerkit-orchestrate-integration. Resume fromlayerkit agent next.
Forbidden
- Dumping secrets, tokens, or raw PII into the runbook
- Claiming steps done without proposal/map evidence
- Instructing the next agent to invent missing fields
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 · 90 lines · 23 tokens per session scan A d06ca9a9d230
layerkit-session-handoff is a skill published in the GitHub repository hariharapanigrahy/layerkit (8 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 641 once invoked, about $0.0001 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
lean-ctx
Use LeanCTX Context Gateway tools to select task-relevant code context, apply supported controls, reuse local knowledge and inspect recorded evidence. Use when lean-ctx MCP tools (ctx) are available or file, search or command output needs a focused view.
lean-ctx
Use LeanCTX Context Gateway tools to select task-relevant code context, apply supported controls, reuse local knowledge and inspect recorded evidence. Use when lean-ctx MCP tools (ctx) are available or file, search or command output needs a focused view.
cs-onboard
Structured C-suite onboarding via a founder interview that captures company context into a persistent file used by all advisory skills. Use when setting up advisory context, refreshing stale context, or onboarding a new executive.
decision-logger
Two-layer memory for executive decisions, separating raw deliberation from approved decisions to prevent hallucinated consensus. Use when logging decisions, reviewing past decisions, or checking overdue action items.
context-engine
Context management engine for AI coding agents. Use when building agent memory systems, optimizing context windows, allocating token budgets, designing RAG pipelines for code, or managing persistent multi-session agent state.
self-improving-agent
Patterns for AI agents that learn from their own execution, detect failure modes, and improve autonomously. Use when building agents that get better over time, managing auto- memory, or designing self-correcting feedback loops.