What is claude-code-delegation?

A guide for preparing Claude Code as a coding worker when Stram has an approved connection for it.

Use it to check Claude Code availability, prepare task instructions, or verify work completed by Claude Code.

It prevents the system from pretending Claude Code is connected when no supported connection exists, and provides a handoff brief instead.

claude-code-delegation — Skill by CodeInfinity1/Stram

Install

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.

Any agent

npx skills add CodeInfinity1/Stram --skill claude-code-delegation

Clone the repo

git clone --depth 1 https://github.com/CodeInfinity1/Stram

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/codeinfinity1/stram/claude-code-delegation/github.svg)](https://agentmods.dev/skills/codeinfinity1/stram/claude-code-delegation)

Your own site

<a href="https://agentmods.dev/skills/codeinfinity1/stram/claude-code-delegation"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/claude-code-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/codeinfinity1/stram/claude-code-delegation"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/claude-code-delegation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 431 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00033	$0.00431
Opus 5.5	$0.00013	$0.00172
Sonnet 5.5	$0.00007	$0.00086
Haiku 4.5	$0.00003	$0.00043

Measured 1mo ago against content hash c2beeb3250f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-code-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.

skills/delegation-agents/claude-code-delegation/SKILL.md · 66 lines

What it actually says

Claude Code Delegation

Purpose

Represent Claude Code as a possible coding worker without pretending it is integrated. Stram must use an owned adapter before executing Claude Code tasks.

When To Use

Use when the user asks to use Claude Code, compare coding workers, or prepare a Claude-oriented handoff.

Inputs And Evidence

Task objective, repo path, constraints, tests, and desired sandbox.
Capability search showing whether a native Claude Code adapter exists.
Handoff prompt or missing-adapter report.

Tool Map

tool_search
capability_surface
write_note
codex_cli_plan
coding-agent

Workflow

Check whether Stram exposes a native Claude Code tool or configured adapter.
If missing, say the adapter is not implemented and prepare a reusable handoff brief.
If implemented later, require approval and bounded sandbox execution.
Verify any delegated output locally.
Prefer existing codex_cli_* delegation when the user accepts Codex as the worker.

Native Implementation Boundaries

Do not call Claude Code CLI directly unless a Stram-owned adapter/tool exists or the user explicitly requests an approved shell action.
Do not import external reference Claude Code scripts.
Do not treat external installation as native integration.

Safety And Approval

Delegated coding tools can modify files; require approval and scoped workdirs.
Do not pass secrets.
Preserve dirty worktrees.

Verification

Capability status must prove whether native support exists.
Handoff briefs are drafts, not executed work.
Any executed result needs local verification.

Failure Modes

Claiming Claude Code ran when only a prompt was drafted.
Delegating too much context.
Skipping local verification.

References

Shortlist item: claude-code-delegation.
Upstream inspiration: external reference Claude Code references only.

Changes

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 · 66 lines · 33 tokens per session scan A c2beeb3250f3

Subscribe to this mod's changes

claude-code-delegation is a skill published in the GitHub repository CodeInfinity1/Stram (11 stars, last pushed 2mo ago), licensed MIT. It adds 33 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.

Building agents ai-agent ai-agents ai-tools desktop-automation desktop-automation-software desktop-automation-windows

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.

Netw0rkNoob/VulnClaw · 32 tokens

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.

AlpacaLabsLLC/skills-for-architects · 37 tokens

authentication-patterns

OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.

travisjneuman/.claude · 28 tokens

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.

WrongStack/WrongStack · 45 tokens

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.

alivecontext/alive · 57 tokens

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…

nitinjain999/platform-skills · 81 tokens