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 claude-world/director-mode-lite --skill session-relaygit clone --depth 1 https://github.com/claude-world/director-mode-liteWrote 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/claude-world/director-mode-lite/session-relay)<a href="https://agentmods.dev/skills/claude-world/director-mode-lite/session-relay"><img src="https://agentmods.dev/badge/skills/claude-world/director-mode-lite/session-relay/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/claude-world/director-mode-lite/session-relay"><img src="https://agentmods.dev/badge/skills/claude-world/director-mode-lite/session-relay.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 106 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00082 | $0.01080 |
| Opus 5 | $0.00041 | $0.00540 |
| Sonnet 5 | $0.00016 | $0.00216 |
| Haiku 4.5 | $0.00008 | $0.00108 |
Grade A, and why
session-relay scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-CLI Session Relay
Move work between Claude Code, Codex CLI, and Grok Build through a portable handoff packet. A relay starts a new native session in the receiving CLI; it does not pretend that vendor session IDs or private conversation histories are interchangeable.
Resolve the relay
Prefer the first available implementation:
<project>/.director-mode/bin/director-relay;$HOME/.claude/bin/director-relayfrom Bootstrap Kit;scripts/director-relay.pybeside thisSKILL.mdfor plugin-only use.
If only the bundled script exists, invoke it with python3. Do not install a
hook or change a permission setting just to use the relay.
Leave a packet
Summarize the current state from repository evidence, then run:
ROOT="${CLAUDE_PROJECT_DIR:-${GROK_WORKSPACE_ROOT:-}}"
[[ -n "$ROOT" ]] || ROOT="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
RELAY="$ROOT/.director-mode/bin/director-relay"
[[ -x "$RELAY" ]] || RELAY="$HOME/.claude/bin/director-relay"
"$RELAY" create \
--from <claude|codex|grok> \
--to <claude|codex|grok> \
--goal "The outcome the user requested" \
--summary "The concise current state" \
--completed "One completed result" \
--decision "One decision and why it was made" \
--next "The first concrete next step" \
--verification "A command and its actual result" \
--blocker "A real blocker, if any"
Repeat list flags as needed. The tool captures branch, HEAD, git status --short, and diff statistics. It deliberately does not copy file contents,
credentials, environment variables, or raw transcripts.
If a native session ID is available, add --session-id; it remains metadata
for the source CLI and is never sent to another vendor as a resume token.
For a second or later handoff in the same chain, add --parent to link the new
packet to the project's current latest.json, or --parent <packet.json> to
name a specific parent. Protocol v2 records the root packet, parent, hop, and
route while remaining able to read v1 packets.
What ships with it
3 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.
- 9d ago First seen · 109 lines · 82 tokens per session scan A ee058d5d1197
session-relay is a skill published in the GitHub repository claude-world/director-mode-lite (81 stars, last pushed 9d ago), licensed MIT. It adds 82 tokens to every session and 1,080 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 2026-08-30.
Other skills, from other repositories
lark-workflow-standup-report
A Feishu (Lark) workflow that combines calendar events with unfinished tasks into a daily schedule summary. Feishu is a workplace collaboration app with calendar and task features.
lark-attendance
A tool for checking an employee's own Feishu attendance and clock-in records. Feishu is a workplace collaboration platform that also provides work-time tracking.
human-ai-schedule
Co-author doctrine for shared, half-hour-block daily schedules. Make sure to consult this skill whenever working in a dated daily log, journal, retro, or coordination file shared with a coworker — even if the user only says "log this at 11:00" or "what did we say last Tuesday." Default behavior of dumping procedural…
concise
Concise communication mode. Cuts 60-70% of output tokens while keeping natural, readable English. Drops filler, hedging, and pleasantries but maintains grammar and sentence flow. Elaborate on request -- ask for detail and get it, then auto-return to concise. Use when user says "concise mode", "be concise", "less…
lark-im
A tool for using Feishu instant messaging and group chats. It works with messages, replies, threads, files, reactions, bookmarks, members, and interactive message cards.
lark-workflow-meeting-summary
A workflow for collecting meeting records from a chosen period and producing a structured summary, using Lark's meeting and document services.