hyperbrief-trigger-check

hyperbrief-trigger-check is a skill for Claude Code from SoliEstre/EstreGenesis. It costs 406 tokens per session (4,266 once invoked), scanned A, original, Apache-2.0.

A short decision-escalation check for an agent workflow. It determines how much information to give before asking a user to decide, approve, or choose something.

In plain words
What is it for?
It is for deciding whether to provide a minimal explanation, a fuller brief, or a blocking summary before requesting user input.
Why use it?
It helps match the amount of explanation to the importance and risk of the decision, while identifying cases that should be handled automatically or paused.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: names the AskUserQuestion tool.

Part of the hyperbrief plugin — 3 skills shipped together

Good fit It is for deciding whether to provide a minimal explanation, a fuller…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/soliestre/estregenesis/hyperbrief-trigger-check
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 SoliEstre/EstreGenesis --skill hyperbrief-trigger-check
Clone the repo
git clone --depth 1 https://github.com/SoliEstre/EstreGenesis

Made for: Claude Code.

Or install hyperbrief, the plugin that ships this one along with the rest of its 3 skills.

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 hyperbrief-trigger-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/soliestre/estregenesis/hyperbrief-trigger-check.svg)](https://agentmods.dev/skills/soliestre/estregenesis/hyperbrief-trigger-check)
Your own site
<a href="https://agentmods.dev/skills/soliestre/estregenesis/hyperbrief-trigger-check"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/hyperbrief-trigger-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 406 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,266 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 $0.00406 $0.04266
Opus 5 $0.00203 $0.02133
Sonnet 5 $0.00081 $0.00853
Haiku 4.5 $0.00041 $0.00427

Measured today against content hash 3ad6c60dfdf1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

hyperbrief-trigger-check 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.

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.

plugins/hyperbrief/skills/hyperbrief-trigger-check/SKILL.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hyperbrief Trigger Check — the escalation gate

You are about to ask the user a decision question, OR Superscalar just opened a write/deploy/send lane, OR an inbound DECISION_REQUEST arrived. Before composing the message, run this 30-second rubric.

1. Trigger detection

Run this skill if ANY of these apply:

  • Next assistant message will contain 괜찮을까요 / 할까요 / should we / which (one|option) / approve / confirm / choose between / OK to / similar decision-soliciting patterns.
  • Superscalar fan-out just opened a write/deploy/send lane (Superscalar's irreversibility barrier touches a default-forbidden action).
  • Inbound A2A is CUSTOM/DECISION_REQUEST requiring response.
  • About to call AskUserQuestion tool.

Skip if:

  • All fan-out lanes are read-only (no side effects).
  • This is a continuation of an already-decided plan within the same approved Phase (Constellation §4: "no confirming planned dispatch").

1.5 Audience-profile command routing (v0.6+)

Independent of the escalation rubric, certain user inputs are audience-profile commands that must be forwarded to the hyperbrief skill (which owns AudienceProfileFallback IR population) for parsing + persistence, regardless of whether a decision is being made.

Recognized command shapes (parse BEFORE the escalation rubric; if matched, route AND continue):

  • Tone profile: L<a>.<b>.<c> (e.g. L1.1.1, L2.2.2) — sets audience_profile_fallback.tone_profile.
  • term_pairing command (v0.6, additive): L<a>.<mode>.<scope>[suffix] where:
    • mode{E, I, N} (every / initial / none).
    • scope{C, D, B, R} (conversation / document / board / review) — multi-scope via + (e.g. C+B), or shortcut A (= C+D+B+R).
    • optional suffix: ! (force retroactive_apply = Y), ? (force retroactive_apply = prompt).
    • Examples: L1.I.C / L1.E.A / L2.N.D / L1.I.C+B / L2.E.D! / L1.I.A?.
  • Combined (single token, dot-chained): tone command followed by term_pairing command in the same utterance — both apply.

Read the full file on GitHub · 212 lines

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 Changed 3ad6c60dfdf1
  2. 6d ago First seen · 212 lines · 406 tokens per session scan A fc19c2e84441

Subscribe to this mod's changes

hyperbrief-trigger-check is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed today), licensed Apache-2.0. It adds 406 tokens to every session and 4,266 once invoked, about $0.0020 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.

Related

Other skills, from other repositories

update-agent-context

This skill should be used to keep CLAUDE.md, AGENTS.md, and the skill files themselves compact, current, and internally consistent. It runs in three phases: Phase 1 performs a one-time structural refactor of CLAUDE.md using a Karpathy-inspired behavioral scaffold and derives AGENTS.md from it by stripping Claude…

mostlyharmless-ai/watercooler · 203 tokens

watercooler-onboarding

Bootstrap Watercooler memory for a repository by inspecting local code, docs, CI, git history, and existing Watercooler threads, then writing a small set of durable, provenance-backed seed threads that future agents can query and extend. Use when entering a repo for the first time, seeding a repo with Watercooler…

mostlyharmless-ai/watercooler · 79 tokens

ppgp

Portable Persistent Goal Protocol for long-running coding-agent work. Use when starting, resuming, handing off, distilling, or closing a substantial software goal across long sessions, context compaction, agent replacement, or other Agent Skills-compatible coding-agent environments.

Fatboy-coder/ppgp · 53 tokens

search-threads

Search threads with filters. Supports filters like role:planner, type:Decision, after:2024-01, thread:topic-name, status:OPEN.

mostlyharmless-ai/watercooler · 35 tokens

watercooler-health

Check watercooler system health — MCP server, baseline graph (T1), git auth, GitHub rate limit, and daemons. Use when syncs break or anything in the watercooler stack behaves unexpectedly.

mostlyharmless-ai/watercooler · 49 tokens

recall

Recall project context or answer questions about history and decisions. Use before starting work, when investigating unfamiliar code, or asking "What was decided about X?" / "Why did we choose Y?".

mostlyharmless-ai/watercooler · 41 tokens