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 commands/kimsanguine/hplan/cogs-sentinelgit clone --depth 1 https://github.com/kimsanguine/hplanWrote 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/commands/kimsanguine/hplan/cogs-sentinel)<a href="https://agentmods.dev/commands/kimsanguine/hplan/cogs-sentinel"><img src="https://agentmods.dev/badge/commands/kimsanguine/hplan/cogs-sentinel.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.00359 |
| Opus 5 | $0.00028 | $0.00179 |
| Sonnet 5 | $0.00011 | $0.00072 |
| Haiku 4.5 | $0.00006 | $0.00036 |
Grade A, and why
cogs-sentinel 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 5d 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
/cogs-sentinel — COGS p50/p90 결정론 게이트
Running for: $ARGUMENTS
이 커맨드는 hplan/cogs-sentinel 스킬을 즉시 호출합니다.
Instructions
hplan/cogs-sentinel스킬을$ARGUMENTS로 invoke.- 스킬이 lognormal Monte Carlo 시뮬레이션 (provider 단가 × 예상 사용량 × free-abuse blend).
- 결과:
- p90 margin ≥ 70% → GREEN (build 가능)
- p90 margin 50~70% → CONDITIONAL_GO (가격 인상 또는 모델 라우팅 필요)
- p90 margin < 50% → RED (단가 구조 재설계 필수)
예시
/cogs-sentinel --provider anthropic --model claude-sonnet-4-6 \
--tokens-in 3000 --calls 40 --arpu 29
Output Format
p50 margin, p90 margin, free-user abuse 영향, 그리고 GREEN / CONDITIONAL_GO / RED 판정과 다음 조치를 반환합니다.
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.
- 5d ago First seen · 32 lines · 56 tokens per session scan A 359e27a2299c
cogs-sentinel is a command published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 19d ago), licensed MIT. It adds 56 tokens to every session and 359 once invoked, about $0.0003 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 commands, from other repositories
research
Professional equity research analysis with institutional-grade formatting.
tax-review
Tax-filing compliance check — invokes tax-reviewer to produce TM-tax-{slug}.md with MeF e-file schema, Form 8879, PTIN/Circular 230, and IRC §7216 consent gaps.
compare
Compare two or more payment providers head to head for a concrete situation — real fees on a real amount, coverage, onboarding time, and what PagoKit can actually build for each.
add
Add a second payment provider alongside an existing integration, without touching the one already running.
search-flights
Search award flight availability across airlines.
radar-start
启动 BTC News Radar 的采集与看板.