Borrowing it
Nothing to install: this file belongs to sussdorff/timing-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sussdorff/timing-cli/main/.agents/skills/context-handoff/SKILL.mdgit clone --depth 1 https://github.com/sussdorff/timing-cliWrote 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/sussdorff/timing-cli/context-handoff)<a href="https://agentmods.dev/skills/sussdorff/timing-cli/context-handoff"><img src="https://agentmods.dev/badge/skills/sussdorff/timing-cli/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/sussdorff/timing-cli/context-handoff"><img src="https://agentmods.dev/badge/skills/sussdorff/timing-cli/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 | $0.00025 | $0.00832 |
| Opus 5.5 | $0.00010 | $0.00333 |
| Sonnet 5.5 | $0.00005 | $0.00166 |
| Haiku 4.5 | $0.00003 | $0.00083 |
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 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Handoff
Preserve conversation-only knowledge so a fresh chat can resume after /clear.
Inputs
- The current conversation and repository state.
- An exact active hosted issue reference (
owner/repo#N) only when the conversation and current work identify one unambiguously. - The canonical harness session ID for file-backed handoffs.
Outputs
- One persisted handoff containing Purpose, Current State, Decisions and Rationale, Failed Approaches, Important Exact Details, Open Questions, Continuation Point, and Uncertainties.
- One copyable bootstrap sentence naming the exact issue or handoff path.
Workflow
- Treat an issue as active only when this conversation and current work identify exactly one. Never select an issue merely because it is assigned or in progress elsewhere. A repository without a hosted tracker has no issue route.
- Write context another capable agent cannot recover by reading files, Git, or the issue body. Preserve exact errors, response shapes, identifiers, corrections, and rationale when they affect continuation. Keep the handoff contextual, not prescriptive.
- For the issue route, treat the explicit invocation as the mandate, submit the declared external-side-effect Action Proposal, and proceed only after
ALLOW. - For an allowed issue route, start the temporary handoff text with
## Context Handoff <ISO-8601 timestamp>and post it as one comment withccore tracker comment <owner/repo#N> --body "$(cat <handoff-file>)"without editing the issue body. Report success only on anokenvelope. - Otherwise run
uv run --no-project <skill-root>/scripts/resolve_handoff_path.pyfrom the target worktree. Pass--repo-root <exact-root>only as a validated override and--session-id <exact-id>only when automatic harness detection cannot resolve one ID. Stop on an error; never substitute a timestamp or invented ID. - Write to the absolute
data.path(.intake/context-handoff/<session-id>.mdunder the resolved repository root). Whendata.existsis false, create the handoff; when true, append a clearly separated newContext Handoffsection and preserve prior sections. Do not create any other documentation file. - In the persistence summary, state when
data.worktree_localis true that the handoff is worktree-local and will disappear if that worktree is removed. Then return exactly one bootstrap sentence. For a file use:Read <data.path> as context from the previous chat; refresh mutable repository and tracker state, then continue from its Continuation Point.For an issue use:Read the latest Context Handoff comment on <owner/repo#N> (<html_url>); refresh mutable repository and tracker state, then continue from its Continuation Point.ccore tracker showreturns the issue body without comments, so name the issue'shtml_url.
What ships with it
5 files 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 Changed c1fc812cae1e
- 1mo ago First seen · 52 lines · 25 tokens per session scan A dd4154e98fc8
context-handoff is a skill published in the GitHub repository sussdorff/timing-cli (1 stars, last pushed 10d ago), licensed MIT. It adds 25 tokens to every session and 832 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 2026-09-24.
Other skills, from other repositories
Migrate
Intakes external content (notes, CLAUDE.md, Cursor rules, Obsidian/Notion/Apple Notes exports), classifies chunks against the LifeOS taxonomy, and commits with provenance after confidence-tiered approval. USE WHEN /migrate, migrate content, import from other LifeOS, bring in old notes, import Cursor rules, import…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
Profile
View, edit, or clear the LifeOS User Model (PRINCIPALIDENTITY.md) — persistent identity context loaded at session startup. Three intents: View, Edit (identity, goals, constraints, preferences), Clear (reset). Read by Algorithm OBSERVE and skills for personalization. USE WHEN profile, show profile, view profile, who am…
wiki-dashboard
Create dynamic, queryable Obsidian dashboard views using Bases or Dataview. Use for auto-updating tables, indexes, or structured views of vault content; not for ordinary question answering.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
session-compact
AI DevKit · Compact a historical AI coding session with Jev when context is long, work is handed off or resumed, or durable continuation facts and memory candidates need extraction.