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 blakecyze/kanso --skill kanso-handoffgit clone --depth 1 https://github.com/blakecyze/kansoWrote 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/blakecyze/kanso/kanso-handoff)<a href="https://agentmods.dev/skills/blakecyze/kanso/kanso-handoff"><img src="https://agentmods.dev/badge/skills/blakecyze/kanso/kanso-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/blakecyze/kanso/kanso-handoff"><img src="https://agentmods.dev/badge/skills/blakecyze/kanso/kanso-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 | $0.00086 | $0.00932 |
| Opus 5 | $0.00043 | $0.00466 |
| Sonnet 5 | $0.00017 | $0.00186 |
| Haiku 4.5 | $0.00009 | $0.00093 |
Grade A, and why
kanso-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 5d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kanso-handoff
Packages what this session knows into .claude/handoff.md so /clear costs nothing. The file is a baton, not a log: each run overwrites the last, the next session reads it and continues, and nothing else is kept.
The audience is the next agent session, not a person. Density beats politeness; a fact the next session must not re-derive beats a paragraph about how it was derived. Everything in kanso-principles about earning lines applies double here, because every line of the handoff is paid for at the start of every future turn.
What goes in
Header first, one line: date, branch, HEAD short sha. The next session diffs against this to detect drift since the handoff.
Then these sections, each optional, each tight. $ARGUMENTS may narrow the pack to one strand of a mixed session.
| Section | Holds | Rule |
|---|---|---|
| Goal | The task, one or two sentences, user's point of view | Present tense, no history |
| State | Done and verified / done but unverified / not started | Verified means a command ran and passed, nothing softer |
| Decisions | Each with its one-line reason | A decision without the why gets re-litigated next session |
| Files | Load-bearing paths, one line each | Repo-relative; say what each is, not what happened to it |
| Open threads | Numbered next steps, most important first | Imperative, self-contained |
| Dead ends | What was tried and abandoned, and why | Saves the next session from retrying it |
| Verify | Exact commands with expected outcomes | Runnable as written |
What stays out
- Transcript narration. "We then discussed" is the failure mode; the next session was not there and does not care.
- Anything git already records. The diff is in git; the handoff carries what the diff cannot say.
- Secrets, always. No tokens, keys, or credentials, even when they appeared in the session. Name where a secret lives (
op://..., an env var) rather than what it is. - Unfounded certainty. Anything not verified is written as unverified.
- Durable knowledge. Repo guidance belongs in AGENTS.md via
kanso-context; solved-problem notes belong to a memory tool. The handoff dies at the next overwrite.
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.
- 5d ago First seen · 62 lines · 86 tokens per session scan A 68db15ba0c73
kanso-handoff is a skill published in the GitHub repository blakecyze/kanso (3 stars, last pushed 7d ago), licensed MIT. It adds 86 tokens to every session and 932 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 2026-09-05.
Other skills, from other repositories
evolving-status
View Self-Evolving Loop session status, history, and memory metrics.
performance-audit
Full-stack performance health check across 12 dimensions. Rendering, bundles, assets, API/network, algorithms, memory, database, caching, Web Vitals, backend runtime, concurrency, and framework-specific pathologies. Evidence-based Impact Models with confidence tiers and a prioritized optimization roadmap. Switches…
esp32-expert
This skill should be used for ESP32-specific hardware and runtime work in ESP-IDF, Arduino-ESP32, or PlatformIO projects: target/build detection, FreeRTOS tasks and ISRs, memory/DMA, peripherals, power, networking/security, OTA, crash diagnosis, and unattended reliability. Trigger on "debug this ESP32 crash", "review…
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
compound-docs
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.
cross-session-handoff
Read, write, snapshot, and lock .arcgentic/state.yaml across planner, dev, audit, and optional test sessions.