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 agentmods add skills/kevinzai/commander/ccc-handoffnpx skills add KevinZai/commander --skill ccc-handoffgit clone --depth 1 https://github.com/KevinZai/commanderWrote 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/kevinzai/commander/ccc-handoff)<a href="https://agentmods.dev/skills/kevinzai/commander/ccc-handoff"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-handoff.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.02305 |
| Opus 5 | $0.00023 | $0.01153 |
| Sonnet 5 | $0.00009 | $0.00461 |
| Haiku 4.5 | $0.00005 | $0.00231 |
Grade A, and why
ccc-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 4d 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ccc-handoff — Hand Off to a Fresh Session
Core idea: context windows degrade model quality as they fill up. The fix is not "compact harder" — it's "hand off to a fresh chat frequently." This skill writes a dense, information-preserving handoff file and then tells you, explicitly, to open a new chat and resume there. It is meant to be invoked often, not just when a session is dying.
Pattern popularized by Matt Pocock (open a fresh chat frequently instead of letting one session's context degrade).
When to Use
Use this proactively — the whole point is that you run it BEFORE quality degrades, not after:
- After finishing a coherent chunk of work (a feature, a fix, a review pass) — even mid-session
- Before starting an unrelated task in the same chat (topic switch = handoff point)
- The moment you notice the model getting slower, forgetting earlier context, or making mistakes it wouldn't normally make
- Mid-way through a long orchestration run (
$ccc-orchestrate,$ccc-plan-exec) — long multi-step Executor loops are exactly when context degrades fastest; do not wait for the run to finish - End of a work session before closing Claude Code (same use case as
$ccc-save-session, but treat "session end" as just one of many trigger points, not the primary one)
If you are asking "should I hand off now or wait" — the answer is hand off now. Frequency is cheap; degraded output is not.
Relationship to $ccc-save-session and $ccc-resume-session
This skill reuses the exact same file format and location as $ccc-save-session — same ~/.claude/sessions/ directory, same YYYY-MM-DD-<short-id>-session.tmp naming. It does not invent a second format. $ccc-resume-session loads a handoff file with zero changes.
The difference is framing and cadence: $ccc-save-session is typically invoked once, at the natural end of a session. $ccc-handoff is the same mechanic invoked deliberately and repeatedly, as a quality-preservation habit — and it always ends with an explicit instruction to leave the current chat.
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.
- 4d ago First seen · 229 lines · 45 tokens per session scan A 1e2a371bc6ae
ccc-handoff is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 2,305 once invoked, about $0.0002 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
codify-lesson
Detect recurring P2/P3 audit patterns across recent rounds and promote them into lesson cards. Use after round boundaries or when repeated findings appear.
cross-session-handoff
Read, write, snapshot, and lock .arcgentic/state.yaml across planner, dev, audit, and optional test sessions.
evolving-status
View Self-Evolving Loop session status, history, and memory metrics.
system-boot
Auto-activating session startup - reads memory, orients Claude, announces status. Triggers on session start or when user says "continue", "weiter", "resume".
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…
setup-memory
Configure project memory: write CLAUDE.md with architecture context and (Tier 3) set up a self-sustaining .claude/memory/ lifecycle — SessionStart load hook, Stop save-nudge hook, and a /save-memory skill that distills each session. Called by init or standalone to configure the memory pillar. Trigger phrases: "setup…