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.
git clone --depth 1 https://github.com/daddia/claude-for-strategyWrote 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/agents/daddia/claude-for-strategy/escalation-watcher)<a href="https://agentmods.dev/agents/daddia/claude-for-strategy/escalation-watcher"><img src="https://agentmods.dev/badge/agents/daddia/claude-for-strategy/escalation-watcher/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/agents/daddia/claude-for-strategy/escalation-watcher"><img src="https://agentmods.dev/badge/agents/daddia/claude-for-strategy/escalation-watcher.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 | $0.00038 | $0.00317 |
| Opus 5.5 | $0.00015 | $0.00127 |
| Sonnet 5.5 | $0.00008 | $0.00063 |
| Haiku 4.5 | $0.00004 | $0.00032 |
Grade A, and why
escalation-watcher 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 Watcher
Runs weekly by default (Monday 09:00) and also fires after each raid-log update. Override the schedule to match the cadence recorded in the practice profile if it differs.
What it does
-
Reads the current RAID log and the practice profile (
~/.claude/plugins/config/claude-for-strategy/pmo/CLAUDE.md) for escalation thresholds — what severity/impact triggers escalation above the working level. -
Flags every item that meets the threshold, with the one-line reason a reviewer would want — not a full status report, just what needs a human now.
-
Posts the summary to
~~chat. If no chat connector is configured, write the summary to a file in the workspace instead. -
Includes an all-clear footer when nothing crosses the threshold. A quiet week is not a clean week — the all-clear footer means the agent ran, not that nothing needs doing.
Fallback with no ~~chat connected
If no chat connector is configured, still run the read side — scan the RAID log, apply thresholds, and write the escalation summary (or all-clear) to a file. Do not silently skip the run.
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 · 28 lines · 38 tokens per session scan A f7b511dd5d5d
escalation-watcher is an agent published in the GitHub repository daddia/claude-for-strategy (2 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 317 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 agents, from other repositories
project-manager
Project management agent for agile and classic methodologies covering charter drafting, WBS creation, sprint planning, backlog management, status reporting, and retrospectives.
security-auditor
Read-only security audit of a diff or module — exploitable flaws at trust boundaries. Invoke from review, or for a security pass before merge.
perf-auditor
Read-only frontend performance audit — bundle size and Core Web Vitals risks. Invoke from review, or for a performance pass on a web app.
Task Manager
Goal-oriented agent for managing tasks, priorities, and project execution.
drupal-tech-lead
Use this agent when you need expert Drupal technical leadership for architecture decisions, team coordination, and project governance. Examples: designing complex Drupal multisite architectures, establishing coding standards and review processes, creating technical specifications for modules and integrations…
Task Manager
Goal-oriented agent for managing tasks, priorities, and project execution.