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 agentmods add skills/soliestre/estregenesis/hyperbriefnpx skills add SoliEstre/EstreGenesis --skill hyperbriefgit clone --depth 1 https://github.com/SoliEstre/EstreGenesisWrote 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/soliestre/estregenesis/hyperbrief)<a href="https://agentmods.dev/skills/soliestre/estregenesis/hyperbrief"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/hyperbrief.svg" alt="Measured on agentmods" 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 | $0.00350 | $0.08993 |
| Opus 5 | $0.00175 | $0.04496 |
| Sonnet 5 | $0.00070 | $0.01799 |
| Haiku 4.5 | $0.00035 | $0.00899 |
Grade A, and why
hyperbrief 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hyperbrief — 8-section decision brief generation
You are about to produce a Hyperbrief because hyperbrief-trigger-check returned FULL_HYPERBRIEF, SUMMARY_BRIEF (v0.8 — the default floor, §0.5 below), DEEP_BRIEF (v0.9 — request-only, §0.6 below), or MINIMAL_BRIEF (Cynefin chaotic). Read the verdict first and take the matching pipeline — §0 for a full brief, §0.5 for a summary, §0.6 for a deep brief. Running the 9-section pipeline on a SUMMARY_BRIEF verdict is not a safe over-delivery: the tier exists because a brief cheap enough to always emit is what closes the gap, and spending full-brief cost on every decision is the alert-fatigue failure §2.4 guards against.
Core invariant: you emit JSON IR only. The renderers (or the templates as fallback) produce MD and HTML. Do NOT write MD or HTML directly — it causes representation drift and turns the 8 sections into markdown cosplay.
v0.6 compatibility note: This skill targets schema v0.6 (4 additive optional slots:
evaluation_lenses,recommended_methodology,maturity_anchor,term_pairing). v0.5.6 callers/IRs remain valid — every v0.6 slot is optional. Omit any slot whose trigger condition (see §1.v06) does not fire.
0. Generation pipeline (staged, NOT single-shot)
1. compute escalation 4-score + classify reversibility, Cynefin domain, RAPID roles → §0
2. draft §1 (context horizon) + §6 (decision prompt) ← frame the question first
3. draft §2 (blast radius) + §3 (incremental path) + §4 (why blocks)
4. draft §5 (consequences — heaviest section: 7 sub-blocks)
5. draft §7 (decision tree — meta-branch + 3 root nodes + Cynefin-adaptive format)
6. derive §8 (recommendation) as a FUNCTION of §7 — cite ≥ 1 node ID
7. self-critique: name 3 omissions → patch IR
8. validate IR against schema/hyperbrief.schema.json
9. render → emit Constellation DECISION_REQUEST + HyperbriefCard pair
10. register §9 Decision Capture (revisit_date + ledger_pointer)
Single-shot 8-section generation is discouraged — sections downstream of §5 collapse to hand-waving when the LLM holds all 8 in working memory simultaneously.
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.
- 5d ago First seen · 377 lines · 350 tokens per session scan A 250f5f192277
hyperbrief is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed today), licensed Apache-2.0. It adds 350 tokens to every session and 8,993 once invoked, about $0.0018 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.
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…
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…
search-threads
Search threads with filters. Supports filters like role:planner, type:Decision, after:2024-01, thread:topic-name, status:OPEN.
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.
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.
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?".