Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add jhlee0409/omni-harness-kit/plugin install harness-kitWrote 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/jhlee0409/omni-harness-kit/handoff)<a href="https://agentmods.dev/skills/jhlee0409/omni-harness-kit/handoff"><img src="https://agentmods.dev/badge/skills/jhlee0409/omni-harness-kit/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/jhlee0409/omni-harness-kit/handoff"><img src="https://agentmods.dev/badge/skills/jhlee0409/omni-harness-kit/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 | $0.00084 | $0.00452 |
| Opus 5 | $0.00042 | $0.00226 |
| Sonnet 5 | $0.00017 | $0.00090 |
| Haiku 4.5 | $0.00008 | $0.00045 |
Grade A, and why
handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
handoff
Capture EVERYTHING a fresh session needs to resume — it has none of your current context, so be concrete (paths, commands, the original ask verbatim), not vague.
- Locate the target. If there is an active spec (a
specs/<date>-*/context.mdmatching this work), write into its## 0. Resume hereblock. Otherwise write.claude/handoff.md. - Fill the resume block (replace it idempotently — don't stack copies):
- Original ask (verbatim): the user's actual request, not your paraphrase.
- Phase / N of M: where in the plan you are.
- Files touched: the real paths changed so far (
git status --short). - Next command: the exact next action (a command, or "edit X to do Y").
- In-flight decisions: anything decided but not yet obvious from the code.
- Don't redo: work already done that a fresh session might wrongly repeat.
- Use the marked-block updater so a re-handoff replaces the block:
printf '%s' "$BLOCK" | bash "${CLAUDE_PLUGIN_ROOT}/skills/introspect/update-block.sh" <file> '<!-- resume:start' '<!-- resume:end -->' - Print the exact
/harness-kit:pickupcommand to run in the fresh session.
A handoff is only as good as a fresh session's ability to resume from it ALONE — write for a reader who saw none of this.
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.
- 10d ago First seen · 33 lines · 84 tokens per session scan A 807e1742fb4d
handoff is a skill published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 452 once invoked, about $0.0004 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
alive:system-cleanup
The world feels messy. Stale tasks, orphan folders, v2 remnants, unsaved sessions — entropy is accumulating and needs to be addressed before it compounds. Scans across all walnuts, then surfaces issues one at a time.
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.
alive:settings
The human wants to adjust how the system behaves — not what it contains, but how it feels. Voice, rhythm, preferences, walnut-level config, full permissions toggleable, named squirrel config, action logging toggle. The system adapting to them. Routes to preferences.yaml or walnut config.yaml depending on scope. For…
cco-clean
Clean up old tracking data and reset statistics.
tokenhabit
A coaching tool that finds habits in past coding-agent conversations that waste tokens, the text units used to process requests and responses, and suggests ways to reduce that waste.
ccc-spawn
Click-first spawn hub — spin isolated work into its own session on demand: a spawntask chip in Cowork, a /spawn peer in the CLI. Also routes to $ccc-fleet or $ccc-relay.