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 jeremylongworth-source/AgentSkills --skill escalation-packgit clone --depth 1 https://github.com/jeremylongworth-source/AgentSkillsWrote 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/jeremylongworth-source/agentskills/escalation-pack)<a href="https://agentmods.dev/skills/jeremylongworth-source/agentskills/escalation-pack"><img src="https://agentmods.dev/badge/skills/jeremylongworth-source/agentskills/escalation-pack/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/jeremylongworth-source/agentskills/escalation-pack"><img src="https://agentmods.dev/badge/skills/jeremylongworth-source/agentskills/escalation-pack.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 | $0.00051 | $0.00381 |
| Opus 5.5 | $0.00020 | $0.00152 |
| Sonnet 5.5 | $0.00010 | $0.00076 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
escalation-pack 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.
What it actually says
Escalation Pack
Core Workflow
- Identify why escalation is needed and what decision or action is requested.
- Summarize the customer impact, severity, affected product area, environment, timeline, and current status.
- Collect evidence: reproduction steps, observed results, expected results, redacted logs, sanitized screenshots, account context, related tickets, and prior attempts.
- State what support has already tried and what remains unknown.
- Route to the correct owner using escalation rules when available.
- Draft a concise internal handoff and a separate customer update if requested.
Safety Rules
- Do not expose internal escalation notes to the customer unless rewritten for customer-facing use.
- Do not assign severity as final when policy evidence is missing.
- Do not promise a fix, credit, refund, workaround, or timeline without owner approval.
- Do not include secrets, tokens, passwords, full payment data, or unnecessary customer personal data in escalation notes.
- Escalate immediately for security, privacy, data loss, broad outage, payment, legal, or executive-account risk.
Deliverable Shape
For escalations, provide:
- Escalation reason
- Severity and customer impact
- Requested owner and decision
- Evidence package
- Steps already tried
- Unknowns and blockers
- Suggested internal handoff
- Optional customer update draft
References
- Read
references/escalation-pack-checklist.mdwhen preparing support, engineering, billing, security, legal, or leadership escalations.
What ships with it
2 files 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.
- 1mo ago First seen · 50 lines · 51 tokens per session scan A 380be6e91e37
escalation-pack is a skill published in the GitHub repository jeremylongworth-source/AgentSkills (1 stars, last pushed 17d ago), licensed MIT. It adds 51 tokens to every session and 381 once invoked, about $0.0002 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.
Other skills, from other repositories
bug-report-writing
Use when any case fails or you reject a criterion - what goes in the reviewcriterion note, the failed case and the numbered needrevision comment, with severity.
issue-authoring
Draft or refine IDD-ready GitHub issues, roadmap issues, and sub-issues before the normal IDD execution loop begins. Use when a request is too large or ambiguous for one reviewable change, when work needs decomposition or dependency encoding, or when the user asks for issue drafting, roadmap planning, or…
support-ticket-triage
Triage support tickets by pulling helpdesk context, searching issue trackers and knowledge bases in parallel, classifying the issue, and giving reps a recommended next action.
github-issue-triage
Triage a GitHub issue by verifying all factual claims against running code, assessing roadmap fit, then posting a structured response comment with confirmed findings, stale corrections, a recommendation, and concrete test steps.
bug-report
Extract a structured bug report from a support ticket and create a Linear issue.
reproducer
For a single issue identifying a code-level bug, extract the reporter's example code from the issue body, adapt it to run on the current , execute via , and compose a verdict.json describing the observed behaviour vs the expected failure. Read-only on the tracker — produces evidence, never posts. Invoked by…