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 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/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/kevinzai/commander/ccc-handoff"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 4 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00061 | $0.01878 |
| Opus 5.5 | $0.00024 | $0.00751 |
| Sonnet 5.5 | $0.00012 | $0.00376 |
| Haiku 4.5 | $0.00006 | $0.00188 |
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 6d 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 — 157 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
CC Commander · $ccc-handoff · a resumable handoff file plus an explicit instruction to continue in a new chat.
Output quality drops as a context window fills. This skill preserves the session's state in a file and moves the work to a fresh chat. Run it often, at natural boundaries, not only when a session is failing.
When to use / when not to
Use it:
- 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. A topic switch is a handoff point.
- As soon as the model slows down, forgets earlier context, or makes mistakes it normally would not.
- Mid-way through a long orchestration run (
$ccc-orchestrate,$ccc-plan-exec, a Workflow run). Long multi-step executor loops degrade context fastest; do not wait for the run to finish. - At the end of a work session. This overlaps
$ccc-save-session; session end is one trigger among many here.
If the question is "hand off now or wait", hand off now. Frequent handoffs are cheap; degraded output is not.
Do not use it to summarize for a human reader (use $ccc-standup) or to compact in place. This skill ends the current chat's working life.
Relationship to $ccc-save-session and $ccc-resume-session
The file format and location are identical to $ccc-save-session: the ~/.claude/sessions/ directory, YYYY-MM-DD-<short-id>-session.tmp naming, and the same section set. There is no second format. $ccc-resume-session loads a handoff file unchanged.
The difference is cadence and ending. $ccc-save-session usually runs once at the end of a session. $ccc-handoff is the same mechanic used repeatedly as a quality habit, and it always ends by telling the user to leave this chat.
What happens
1. Gather context
Collect, before writing anything:
git status --short
git diff --stat
git log --oneline -10
- Read the files modified this session (from the diff above or from the conversation).
- Review what was discussed, attempted and decided.
- Note every error hit and whether it was resolved.
- Record the current test/build result if relevant. Use the result already observed this session; if none was observed, write "not run this session" rather than claiming a status.
- If an orchestration is in flight (
$ccc-orchestrate,$ccc-plan-exec, a Workflow run, a Routine or a/loop), capture the exact phase/step the executor is on and how to inspect it (/workflows,/schedule), not just the overall goal.
What ships with it
1 file 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.
- 6d ago Changed · -72 lines · +16 tokens per session 3232735baab9
- 1mo 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 today), licensed MIT. It adds 61 tokens to every session and 1,878 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
context-hygiene
Use when starting a project, reading project documentation or history, or resolving conflicts between documents. For current state, read only the latest documents designated by the project; do not proactively read archives; do not duplicate the spec; use long-term memory only for environment, people, and preferences…
agent-memory-mcp
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
report
Writes the session final report to a file, then prints only the path and a one-line summary. Fires when the prompt contains "Report per memstack:report", and also when the prompt begins with a standing trigger configured through MEMSTACKREPORTONTASKPROMPTS or MEMSTACKREPORTTRIGGERS. Dormant otherwise.
token-optimization
Use when the user says 'token optimization', 'save tokens', 'context window', 'reduce tokens', 'token stack', or 'TokenStack', or asks about extending context window capacity. Covers TokenStack, the built-in compression proxy that shrinks Claude Code tool output before it reaches the Anthropic API. Do NOT use for…
magic-compact
Compact this Claude Code session.
debt-ops-init
Write or refresh a "Tech debt operations" section in the project's AGENTS.md so the team shares one source of truth for debt-ops disciplines. Run ONLY when the user explicitly asks to set up, install, or initialize debt-ops disciplines — never auto-invoke. Idempotent; only the managed section changes, other sections…