agentmods.dev

tp-escalate

tp-escalate is a skill for Claude Code from CurtisThe/three-pillars-plugin. It costs 48 tokens per session (1,784 once invoked), scanned A, original, Apache-2.0.

A procedure for asking another agent to review a stuck design decision or recording feedback about an earlier ruling. It follows a shared escalation process and keeps the result with the relevant design run.

In plain words
What is it for?
Use it to escalate an unresolved design question, submit a stop report, or agree with or challenge a previous ruling.
Why use it?
It provides a defined way to handle uncertainty instead of silently guessing. It also prevents escalation records from being written in the wrong worktree, a separate working copy of the project.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the three-pillars plugin — 39 skills, 58 agents shipped together

not rated 4repo yesterday A scan 48 tokens original Apache-2.0

Good fit Use it to escalate an unresolved design question, submit a stop report, or agree with or challenge a previous ruling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/curtisthe/three-pillars-plugin/tp-escalate
View source ↗ CurtisThe/three-pillars-plugin
Install

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.

Any agent
npx skills add CurtisThe/three-pillars-plugin --skill tp-escalate
Clone the repo
git clone --depth 1 https://github.com/CurtisThe/three-pillars-plugin

Made for: Claude Code.

Or install three-pillars, the plugin that ships this one along with the rest of its 39 skills, 58 agents.

Wrote 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.

agentmods badge for tp-escalate

README.md
[![agentmods](https://agentmods.dev/badge/skills/curtisthe/three-pillars-plugin/tp-escalate/github.svg)](https://agentmods.dev/skills/curtisthe/three-pillars-plugin/tp-escalate)
Your own site
<a href="https://agentmods.dev/skills/curtisthe/three-pillars-plugin/tp-escalate"><img src="https://agentmods.dev/badge/skills/curtisthe/three-pillars-plugin/tp-escalate/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.

agentmods 80×15 button for tp-escalate

Your own site · 80×15
<a href="https://agentmods.dev/skills/curtisthe/three-pillars-plugin/tp-escalate"><img src="https://agentmods.dev/badge/skills/curtisthe/three-pillars-plugin/tp-escalate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,784 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.01784
Opus 5.5 $0.00019 $0.00714
Sonnet 5.5 $0.00010 $0.00357
Haiku 4.5 $0.00005 $0.00178

Measured today against content hash 0bf6aa10cd42, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tp-escalate 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 today.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/seat_brief.py, scripts/test_seat_brief.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/tp-escalate/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/tp-escalate

The seat's half of the escalation protocol in skills/_shared/escalation.md: hand a question or a stop report to a Fable agent (tp-finalizer), get a pillar-grounded ruling, and either relay it to the run or put the one unresolved question to the operator. Feedback on a past ruling records itself and can propose a lesson.

Read skills/_shared/escalation.md first — it is the whole protocol (principles, the run's half, commit points, the card, the hook, the lesson layers). This skill is the seat's procedure on top of it; it never restates the rules, only the commands.

Steps

  1. Run first-run preflight per skills/_shared/first-run.md.

  2. Refuse in a design worktree. If the current branch is tp/*, stop: /tp-escalate runs in the base checkout only — a run's rulings live on its own branch and the seat must not write them. Tell the user to run this from the base checkout (or route the question through the run itself per skills/_shared/escalation.md).

  3. Parse the argument. Either an escalation: {slug|seat} with --question <text> or --stop <json> (a run's finalizer stop JSON); or feedback: feedback <ruling-id> agree|disagree <reason>. {slug} is validated [a-z0-9-] per skills/_shared/validate-name.md; seat means a question with no design of its own.

  4. Feedback path — python3 "$TP_ROOT"/skills/_shared/ruling_cli.py feedback --id <ruling-id> agree|disagree --reason <reason>, then step 8 (one lesson round) when the feedback disagrees with the ruling or the user asks for one. Otherwise commit (step 9) and stop.

  5. Build the stop — the seat stop carries the fleet context (in-flight registry, orchestration handoff, the run's newest ruling, read from the run's worktree or tp/<slug>, never this checkout):

    python3 "$TP_ROOT"/skills/tp-escalate/scripts/seat_brief.py build --scope {slug|seat} \
  --question-file <f> --kind decision --out stop.json

    A run's own finalizer stop JSON goes in with --stop <f> instead. A fleet trouble verdict enters as --question-file (the verdict summary) with --kind decision.

Read the full file on GitHub · 122 lines

Files

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.

Changes

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.

  1. today First seen · 122 lines · 48 tokens per session scan A 0bf6aa10cd42

Subscribe to this mod's changes

tp-escalate is a skill published in the GitHub repository CurtisThe/three-pillars-plugin (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 1,784 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 2026-10-17.

Building agentsPlanning
Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens