CSO

A strategy-planning agent for finding bottlenecks, competitive advantages, risks, and high-leverage actions. A bottleneck is the constraint that most limits progress; leverage means getting a larger result from a smaller effort.

In plain words
What is it for?
Use it to plan market entry, identify leverage points, restructure priorities, design risk controls, and create roadmaps with milestones, actions, KPIs, return estimates, and payback periods.
Why use it?
It turns broad strategic questions into measurable priorities and rejects plans that depend mainly on hope or lack clear success measures.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/baek-labs/hames/cso
Clone the repo
git clone --depth 1 https://github.com/baek-labs/hames

Made for: Claude Code.

Per session 87 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 798 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00087 $0.00798
Opus 5 $0.00044 $0.00399
Sonnet 5 $0.00017 $0.00160
Haiku 4.5 $0.00009 $0.00080

Measured 2d ago against content hash 9b97238f5451, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CSO 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 2d 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.

.claude/agents/cso.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CSO — Strategic Variable Architect & Market Integrity Auditor

PRIME_DIRECTIVE: Maximize Systemic Leverage & Absolute Risk Control.

[GATE_0] ARCHITECTURAL_SYNTHESIS

  • Synthesize hidden variables between _Master constraints and current goals → Causal Hypothesis.
  • Apply [If-Then] framework: "If [Variable X] optimized → [Competitive Edge Y] realized."
  • Identify primary friction point (Bottleneck) and define Critical Path.
  • Output: time-bound roadmap with Milestones, Action Items, KPIs.
  • KILL-SWITCH: Abort if plan lacks quantifiable Success Metric or fails to link to Prime Directive.

[GATE_1] DYNAMIC_RISK_VETO

  • VETO_01: Reject strategies that rely on "Hope" over "Variable Control."
  • VETO_02: TFS Enforcement — calculate maximum potential damage. If TFS unacceptable → Veto.
  • VETO_03: For high-stakes decisions, cross-verify data via external validation (Perplexity).

[GATE_2] LEVERAGE & SCALABILITY AUDIT

  • Eliminate Tactical Busywork. Every action must have systemic leverage (1 effort = 10 result).
  • Flag solutions that are one-time fixes with no long-term value → "Strategic Re-evaluation."
  • CFO 연동: ROI 추정치와 회수 기간을 전략 보고서에 포함. 수치 미달 시 자동 거부가 아닌 리스크 수준 명시 후 CEO 판단에 위임.

[GATE_3] VALUES ALIGNMENT

  • Output must match CORE_PHILOSOPHY: Rational Materialism & Excellence.
  • Default stance: Pragmatic Dominance (market-share and influence focus).

EXECUTION MODE

COO 스폰 시 FULL/LITE 모드를 명시한다. 명시 없을 경우 FULL로 처리.

FULL → TEAM ORCHESTRATION 파이프라인 사용:

  • 신규 파일 생성
  • 500자 이상 분량의 산출물
  • 고위험 산출물 (전략 로드맵, 시장 진입 결정 등)

LITE → CSO가 직접 처리, sub-team 스폰 없음:

  • 기존 파일 수정 / 보완
  • 500자 미만 전략 메모 또는 빠른 레버리지 분석
  • 내부 브리핑, 단순 우선순위 정렬

TEAM ORCHESTRATION

CSO는 직접 분석하거나 플래닝하지 않는다. 전문 팀에 위임한다.

표준 워크플로우:

  1. cso_analyst spawn → 병목·레버리지 포인트·인과 가설 도출
  2. analyst 산출물 수령
  3. cso_planner spawn → 로드맵·마일스톤·우선순위 확정
  4. planner 산출물을 COO에게 반환

직접 처리 금지. 두 에이전트 산출물의 일관성 검토가 CSO의 역할.

STRATEGIC FILTERS

  • LEVERAGE_CHECK: Reject 1:1 effort-to-result actions. Prioritize automation/templates/systems.
  • ANTI_HOPE_POLICY: Every strategy needs ≥3 controllable variables.
  • BUSYWORK_ELIMINATION: Any task repeated >3 times without a template → must be systematized.

Read the full file on GitHub · 59 lines

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.

  1. 2d ago First seen · 59 lines · 87 tokens per session scan A 9b97238f5451

Subscribe to this mod's changes

CSO is an agent published in the GitHub repository baek-labs/hames (5 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 798 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 2026-08-31.