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 SoliEstre/EstreGenesis --skill hyperbrief-revisitgit 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-revisit)<a href="https://agentmods.dev/skills/soliestre/estregenesis/hyperbrief-revisit"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/hyperbrief-revisit/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/soliestre/estregenesis/hyperbrief-revisit"><img src="https://agentmods.dev/badge/skills/soliestre/estregenesis/hyperbrief-revisit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00151 | $0.02980 |
| Opus 5 | $0.00076 | $0.01490 |
| Sonnet 5 | $0.00030 | $0.00596 |
| Haiku 4.5 | $0.00015 | $0.00298 |
Grade A, and why
hyperbrief-revisit 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 9d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hyperbrief Revisit — close the learning loop
You are scanning the decision ledger for decisions whose revisit_date has arrived (or whose assumed_invariants have been violated), OR a specific decision_id has been handed to you for review.
0. Schema version awareness (v0.6.0)
본 skill 은 schema v0.6.0 인지. v0.5.6 → v0.6.0 변경 사항:
- v0.5.6 IR 도 v0.6 schema 에 valid 유지 (back-compat). 모든 신규 슬롯은 optional — 기존 ledger 항목 마이그레이션 불요.
- 신규 슬롯 4 종 (revisit 시점에 비어있을 수 있음 — 그 자체로 흠결 아님):
section_0_decision_header.evaluation_lenses[]— 같은 결정에 대한 multi-lens 점수 (예: Lens A 모듈 GA / Lens B host marketplace).section_8_recommendation.recommended_methodology[]— 결정에 사용된 평가 방법론 박제 (예:hyperbrief-v1-readiness-rubric).maturity_anchor(top-level, optional) — 자의적 라벨 (v1.0/GA/stable) 에 측정 가능한 anchored 기준.AudienceProfileFallback.term_pairing— tone 프로파일의 표시 정책 + 적용 범위 (mode E/I/N · scope C/D/B/R · retroactive_apply).
- v0.5.6 caller 도 v0.6 skill 호환: 이전 버전 IR 를 그대로 입력해도 본 skill 동작. 신규 슬롯 부재 시 retrospective 질문에서 "옵션으로 채우기" 만 제시 (강제 아님).
1. Trigger conditions
Run this skill if ANY of these apply:
- Session-start / Stop hook / 6h cron tick → scan ledger for
revisit_date <= now AND outcome_actual == null. - Inbound A2A signal contradicts an
assumed_invariantin any active decision's lineage. - User explicitly invokes
/hyperbrief revisit <decision_id>. hyperbriefskill's parent-decision check found a stale parent.- v0.6 추가:
maturity_anchor.claimed_label이 부착된 결정의 경우, anchor methodology 의 current_score 가 threshold 를 (재)교차했는지 감지된 시점.
2. Ledger scan
Locate the ledger at one of:
- Standalone:
.agent/_decisions/*.json(one file per decision_id). - Constellation-integrated: Constellation
state.json→decisions[]array, OR SSE endpoint/api/decisions/stream.
For each entry where revisit_date <= now AND outcome_actual == null:
- Load the original IR (full JSON). Schema version 확인 — v0.5.6 / v0.6.0 둘 다 처리. 누락 슬롯은 정상 (back-compat).
- Surface to the user as a
HyperbriefRevisitcard (or inline text in standalone mode). - Block other low-priority work until the user responds (revisit > new work).
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.
- 9d ago First seen · 141 lines · 151 tokens per session scan A 174f0eae3e38
hyperbrief-revisit is a skill published in the GitHub repository SoliEstre/EstreGenesis (8 stars, last pushed 3d ago), licensed Apache-2.0. It adds 151 tokens to every session and 2,980 once invoked, about $0.0008 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…
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?".
wiki
Use this skill when querying workspace knowledge before tasks or running mandatory post-review ingest evaluation and conditional wiki ingestion. Self-learning loop for the workspace.
mem0-integration
Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.
moai-foundation-context
Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows. Use for token budget management, context limits, or session handoff across agents.