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 ychampion/cskill-agents --skill inherited-flags-for-spawned-teammatesgit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/ychampion/cskill-agents/inherited-flags-for-spawned-teammates)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/inherited-flags-for-spawned-teammates"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/inherited-flags-for-spawned-teammates/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/ychampion/cskill-agents/inherited-flags-for-spawned-teammates"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/inherited-flags-for-spawned-teammates.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 | $0.00037 | $0.00539 |
| Opus 5 | $0.00018 | $0.00269 |
| Sonnet 5 | $0.00007 | $0.00108 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
inherited-flags-for-spawned-teammates 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 7d 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Inherited Flags For Spawned Teammates
Domain: multi-agent
Trigger: Apply whenever a teammate or tmux-based sub-agent is spawned and it must inherit the parent’s CLI flags and environment to stay aligned.
Source Pattern: Distilled from reviewed multi-agent coordination and child-runtime patterns.
Core Method
Collect the leader’s active CLI options (permission mode, model override, settings path, inline plugins, teammate-mode, chrome override) via buildInheritedCliFlags, rendering them into --flag value strings that the spawned command receives. Parallelly, spool key environment variables (provider overrides, upstream proxy, credential markers) into buildInheritedEnvVars, giving the new process CLAUDECODE=1, CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1, and any configured provider/proxy keys so the teammate shares the same backend references. Apply both sets when composing the tmux env + command invocation so the teammate behaves identically to its leader.
Key Rules
- Propagate permission mode flags only when plan mode is not required; plan mode takes precedence and should block bypass propagation.
- Always include model, settings, plugin directories, teammate mode, and chrome toggles that the leader specified.
- Forward provider-specific env vars (e.g., MITM proxy, CLAUDE_CODE_USE_BEDROCK) plus canonical teammates flags so spawned shells hit the same endpoints.
- Add
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1andCLAUDECODE=1to signal the child process about the teammate experiment context.
Example Application
When a coordinator spawns a tmux teammate for claude backup, reuse this skill by calling the helper functions, appending the resulting --flag arguments and env KEY=VAL string to the tmux new-session command so the teammate shares flags, models, plugins, and upstream proxy configuration.
Anti-Patterns (What NOT to do)
- Don’t spawn teammates with a blank env—they will default to first-party endpoints and lose plugin context.
- Don’t forget to skip bypass-permissions flags when plan mode is required; inheriting bypass would violate plan-mode guarantees.
- Avoid hardcoding env keys; derive the list from the
TEAMMATE_ENV_VARSconstant so new proxies or secrets get forwarded consistently.
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.
- 7d ago First seen · 29 lines · 37 tokens per session scan A 0212c7d77233
inherited-flags-for-spawned-teammates is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 539 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 2026-09-03.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
genie
Entry point for Genie operations — routes bug reports, questions, and operational commands, resumes existing lifecycle state, and orchestrates work that needs durable planning or coordination. Other ordinary requests bypass the lifecycle with a one-line notice unless the user asks for Genie.
wish
Convert an idea into a structured wish plan with scope, acceptance criteria, and execution groups for work.