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 codex-delegationgit 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/codex-delegation)<a href="https://agentmods.dev/skills/codeinfinity1/stram/codex-delegation"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/codex-delegation/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/codex-delegation"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/codex-delegation.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 | $0.00025 | $0.00431 |
| Opus 5.5 | $0.00010 | $0.00172 |
| Sonnet 5.5 | $0.00005 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
codex-delegation 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.
What it actually says
Codex Delegation
Purpose
Delegate bounded repository work to Codex CLI through native Stram delegation tools while keeping scope, sandbox, approvals, and verification explicit.
When To Use
Use this skill when another Codex run should inspect, implement, or verify a bounded repository task that is too large or parallelizable for the current agent turn.
Tool Map
codex_cli_statuscodex_cli_plancodex_cli_runcodex_capability_status
Workflow
- Use
codex_cli_statusto confirm the CLI is available. - Use
codex_cli_planto let the configured model prepare the handoff, sandbox, approval policy, and verification plan. - Review the generated
codex_cli_runinput before execution. - Use
codex_cli_runonly when the task is explicit, bounded, and appropriate for delegation. - Treat the delegated result as evidence and verify important claims locally.
Safety
- Do not pass secrets, unrelated private context, or broad filesystem scope to delegated tasks.
- Do not ask delegated Codex to push, deploy, delete, or install unless the user explicitly approved that scope.
- Keep implementation delegation approval-gated through
codex_cli_run.
Native Implementation Boundaries
- Use Stram
codex_cli_status,codex_cli_plan,codex_cli_run, andcodex_capability_statusas the native path. - Treat Codex plugin/skill references as instructions or capability discovery, not as imported runtime implementation.
- Delegated output is not authoritative until the current agent verifies files, tests, and git state.
Verification
- Keep read-only delegation for investigation.
- Use workspace-write delegation only when implementation is required.
- Do not pass secrets or unrelated private context into delegated tasks.
- Confirm the local repo state, changed files, test output, and claimed blockers after the delegated run.
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 · 49 lines · 25 tokens per session scan A 8d82c6f4df73
codex-delegation is a skill published in the GitHub repository CodeInfinity1/Stram (11 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 431 once invoked, about $0.0001 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
leadership
Executive leadership expertise for decision-making, change management, crisis management, stakeholder management, team building, and organizational leadership. Use when leading teams, managing change, navigating crises, or developing leadership skills.
product-management
Product management expertise for product strategy, roadmap planning, feature prioritization (RICE, ICE, MoSCoW), customer research, A/B testing, product analytics, and product-market fit. Use when building product roadmaps, prioritizing features, or defining product strategy.
init-project
Bootstrap a new research project. Interview for details, scaffold directory structure, create Overleaf symlink, initialise git, and create project context files.
shared-monorepo-turborepo
Turborepo, workspaces, package architecture, @repo/ naming, exports, tree-shaking.
setup
Interactive onboarding that discovers team structure, terminology, development goals, performance and management frameworks, organizational values, and ways of working by crawling Slack, Notion, Google Drive, Gmail, and Calendar. Validates everything with the manager before persisting. Run this first before using any…
workspace
Scaffold and manage the stateless AI workspace — context, packs, repos, and knowledge for multi-repo orchestration.