Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tolgakisaogullari/SumelaOSnpx agentmods add skills/tolgakisaogullari/sumelaos/context-handoffWrote 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/tolgakisaogullari/sumelaos/context-handoff)<a href="https://agentmods.dev/skills/tolgakisaogullari/sumelaos/context-handoff"><img src="https://agentmods.dev/badge/skills/tolgakisaogullari/sumelaos/context-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/tolgakisaogullari/sumelaos/context-handoff"><img src="https://agentmods.dev/badge/skills/tolgakisaogullari/sumelaos/context-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 | $0.00067 | $0.04276 |
| Opus 5 | $0.00034 | $0.02138 |
| Sonnet 5 | $0.00013 | $0.00855 |
| Haiku 4.5 | $0.00007 | $0.00428 |
Grade A, and why
context-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 11d 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
- Detecting context pressure early — not at the wall.
- Choosing the right protocol: clean finish vs. checkpoint park.
- Updating the Second Brain surfaces that actually changed so the next session starts with accurate state.
- Running /evolve pre-check so learning signals aren't lost across session boundaries.
- Generating a handoff prompt the next agent can execute without rereading the entire session history.
Core invariant: The next agent must be able to continue exactly where this session stopped — no reconstruction, no guesswork.
<trigger_conditions> Activate the handoff-assessment workflow when ANY of these conditions are true:
- System signal: Context compaction warnings appear, or significant prior message compression is observed.
- Task-count heuristic: You have executed 8+ major tool call sequences (each task counts as one sequence) in the current session.
- Volume heuristic: The session has involved 3+ full reads of large files (>200 lines) AND 2+ code-review cycles.
- Sprint milestone heuristic: A sprint task is marked complete and the remaining task count suggests 2+ tasks still need to be done this session.
- Explicit user trigger: User says "context handoff", "prepare handoff", "new session", "let's continue in a new session", "is the context full?" — or the equivalent in any language.
Rule: Activate the assessment — do NOT interrupt the user mid-task. Always complete the current smallest meaningful unit first, THEN assess. </trigger_conditions>
<assessment_workflow> After completing the current task unit, when trigger conditions are met:
-
Assess current state:
- Is there an active sprint plan? (Check
docs/second-brain/artifacts/plans/if not in context.)- If the sprint plan or recent session context is missing from working memory, run the four-tier decision tree before proceeding:
python .sumela/memory-plugins/qdrant-session-memory/scripts/query-qdrant.py "<topic>" --limit 3for session summaries (Tier 1), then_SEARCH_INDEX.mdfor wiki pages (Tier 3). Do NOT rely solely on manual file reads for historical context.
- If the sprint plan or recent session context is missing from working memory, run the four-tier decision tree before proceeding:
- Is the current task FULLY DONE or IN PROGRESS?
- Did the active sprint/project state change? If yes, is
wiki/active-project-context.mdup to date? If no, the session summary +_SEARCH_INDEX.mdupdate may be the correct persistent artifact. - Run
grep -l "^status: pending" docs/second-brain/wiki/_improvement-queue/IMP-*.md 2>/dev/null | wc -l (bash) or @(Get-ChildItem docs/second-brain/wiki/_improvement-queue/IMP-*.md | Select-String "^status: pending").Count (PowerShell) — glob IMP-*.md only, never the whole dirto get the pending count — do NOT read the full file.
- Is there an active sprint plan? (Check
-
Choose protocol:
- Current task is FULLY COMPLETE → Protocol A
- Current task is IN PROGRESS → Protocol B
-
Execute the chosen protocol.
-
Present handoff prompt to user and ask for confirmation. </assessment_workflow>
<protocol_a>
Protocol A — Task Complete, Context Low
Use when: The current task is fully finished and verified.
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.
- 11d ago First seen · 273 lines · 67 tokens per session scan A 8cc2781ed5ae
context-handoff is a skill published in the GitHub repository tolgakisaogullari/SumelaOS (4 stars, last pushed 16d ago), licensed MIT. It adds 67 tokens to every session and 4,276 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…