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 CodeInfinity1/Stram --skill agent-worker-handoffgit clone --depth 1 https://github.com/CodeInfinity1/StramWrote 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/codeinfinity1/stram/agent-worker-handoff)<a href="https://agentmods.dev/skills/codeinfinity1/stram/agent-worker-handoff"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/agent-worker-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/codeinfinity1/stram/agent-worker-handoff"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/agent-worker-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 | $0.00043 | $0.00632 |
| Opus 5.5 | $0.00017 | $0.00253 |
| Sonnet 5.5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
agent-worker-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 1mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Worker Handoff
Purpose
Prepare safe, bounded handoffs to worker agents while keeping Stram responsible for verification and user-facing claims. This adapts external reference codex, claude-code, and opencode delegation workflows.
When To Use
Use when a task is too large for a single foreground loop, benefits from independent review, or specifically asks to use a coding worker.
Inputs And Evidence
- Objective, workspace path, allowed files, constraints, and expected outputs.
- Worker availability and sandbox/approval support.
- Current git state and user changes.
- Verification commands.
Tool Map
codex_cli_statuscodex_cli_plancodex_cli_runmulti_agent_coordinaterun_shell_commandread_filewrite_note
Workflow
- Inspect worker availability and current workspace state.
- Ask the configured model to decide whether delegation is appropriate.
- Prepare a prompt containing objective, scope, constraints, verification, and reporting format.
- Prefer read-only or dry-run-first for inspection and review.
- Execute worker handoff only with approval when the tool requires it.
- Verify worker outputs locally before incorporating them into the final result.
Safety And Boundaries
- Do not pass secrets unless absolutely required and explicitly approved.
- Do not delegate outside the intended workspace.
- Do not allow worker-side push/deploy unless the user explicitly requested it.
Safety And Approval
- Check git status and user-owned changes before handoff.
- Prefer read-only, dry-run, or planning handoffs before write-capable handoffs.
- Require approval for worker commands that mutate files, install dependencies, access networks, use secrets, push, deploy, or run long-lived processes.
- If the worker reports success without verifiable artifacts, treat it as unverified.
Native Implementation Boundaries
- Use Stram Codex CLI status/plan/run, multi-agent board, shell, file, and note tools.
- Claude Code, OpenCode, external reference, and other worker systems are external runtimes; this skill prepares and verifies handoffs rather than importing their code.
- Stram remains responsible for final validation, commit scope, and user-facing claims.
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.
- 1mo ago First seen · 78 lines · 43 tokens per session scan A 262224140bb5
agent-worker-handoff is a skill published in the GitHub repository CodeInfinity1/Stram (11 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 632 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 2026-09-03.
Other skills, from other repositories
android-pentest
A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.
lighting-report-extract
Check reported lighting quantities and results in supplied simulation PDFs without adding repeated calculation surfaces. Use for scoped luminaire inventories and illuminance results; not simulation or compliance.
authentication-patterns
OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.
container-debugging
Diagnose reported container build, startup, network, permission and resource failures. Use when an image or Compose service fails; reproduce against the final image/config and avoid data-destroying cleanup as a workaround.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
pr-review
Comprehensive PR review across six dimensions — cost impact, environment drift, ownership gaps, SOC 2 compliance, deprecated API / version hygiene, and rollback feasibility. Each mode inspects the diff and current file state, reports findings with severity, and recommends concrete fixes. Use when preparing a PR for…