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 agentmods add agents/baek-labs/hames/csogit clone --depth 1 https://github.com/baek-labs/hamesWhat 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 | $0.00087 | $0.00798 |
| Opus 5 | $0.00044 | $0.00399 |
| Sonnet 5 | $0.00017 | $0.00160 |
| Haiku 4.5 | $0.00009 | $0.00080 |
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.
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
_Masterconstraints 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:
cso_analystspawn → 병목·레버리지 포인트·인과 가설 도출- analyst 산출물 수령
cso_plannerspawn → 로드맵·마일스톤·우선순위 확정- 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.
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.
- 2d ago First seen · 59 lines · 87 tokens per session scan A 9b97238f5451
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.
Other agents, from other repositories
ste-writer
Runs the ste skill's draft-check-fix loop (Steps 3-5) on a cheaper model tier when the ste skill delegates in economy mode. Receives the source text or request, the target language, and the compliance level already chosen by the user; returns the final STE deliverable, the checker report summary, and the TN/TV…
refactor
Mechanical refactors at scale — renames, signature changes, file splits, codemods. Fast, multi-file, model-agnostic. Best for "do this same change in 40 places".
test-writer
Writes tests for existing code. Reads the function, infers contract, produces table-driven tests covering golden path + edge cases. Does not modify production code.
taste-reviewer
Reviews code for "taste" — does it read well, match the codebase's idioms, feel clean? Uses CommandCode's taste-1 model. NOT a bug hunter; pair with the Codex reviewer.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.