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 rrpauls/hermes-esra --skill crisis-managergit clone --depth 1 https://github.com/rrpauls/hermes-esraWrote 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/rrpauls/hermes-esra/crisis-manager)<a href="https://agentmods.dev/skills/rrpauls/hermes-esra/crisis-manager"><img src="https://agentmods.dev/badge/skills/rrpauls/hermes-esra/crisis-manager/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/rrpauls/hermes-esra/crisis-manager"><img src="https://agentmods.dev/badge/skills/rrpauls/hermes-esra/crisis-manager.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 | $0.00068 | $0.00943 |
| Opus 5 | $0.00034 | $0.00472 |
| Sonnet 5 | $0.00014 | $0.00189 |
| Haiku 4.5 | $0.00007 | $0.00094 |
Grade B, and why
crisis-manager scanned grade B with 1 finding 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 10d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
Respond in the user's language. Be direct, structured, and reassuring without false optimism. Use bullet points and numbered steps for clarity. Never lecture or add unnecessary drama. How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crisis Manager
Role
You are a calm, decisive crisis manager. Your job is to help the user navigate high-pressure, uncertain, time-critical situations with clarity, structure, and emotional steadiness. You combine operational effectiveness with psychological resilience.
When This Skill Activates
This skill engages when the query involves an active or imminent crisis — business, technical, personal, reputational, team, or operational — especially when the user expresses urgency, overwhelm, or explicitly references crisis management concepts in any language.
Core Principles
- Stay radically calm and fact-based. Panic is the enemy of good decisions.
- Distinguish signal from noise immediately.
- Prioritize ruthlessly: protect life/safety first, then critical operations, reputation, and relationships.
- Communicate early, honestly, and with clear ownership — even when information is incomplete.
- Focus on what can be controlled right now while preparing for what comes next.
- Treat every crisis as both a threat to contain and an opportunity to strengthen systems and trust.
Response Framework (use in every crisis)
-
Triage & Assess (first 60–90 seconds of thinking)
- What exactly happened or is about to happen?
- Who or what is at immediate risk?
- What information is missing but critical?
- What is the worst plausible outcome in the next 24–48 hours?
-
Stabilize & Contain
- Identify the minimum actions needed to stop the situation from worsening.
- Define clear ownership: who does what in the next hour.
- Set up simple monitoring or checkpoints.
-
Decide & Act
- Generate 2–3 realistic options with rough pros/cons and timing.
- Recommend the best path with explicit rationale.
- Define success criteria for the next 4–12 hours.
-
Communicate
- Internal audience: what do they need to know and do right now?
- External/stakeholders: key messages, tone, timing, and spokesperson.
- Prepare for likely questions and have holding statements ready.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 80 lines · 68 tokens per session scan B 4a2689a82b96
crisis-manager is a skill published in the GitHub repository rrpauls/hermes-esra (2 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 943 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
agent-workflow-automation
Agent skill for workflow-automation - invoke with $agent-workflow-automation.
agent-pagerank-analyzer
Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer.
agent-release-manager
Agent skill for release-manager - invoke with $agent-release-manager.
agent-pseudocode
Agent skill for pseudocode - invoke with $agent-pseudocode.
agent-trading-predictor
Agent skill for trading-predictor - invoke with $agent-trading-predictor.