agentmods.dev

retro-lost

retro-lost is a skill for Claude Code from tonydzi/second-brain-starter-kit. It costs 74 tokens per session (7,774 once invoked), scanned A, original, MIT.

A retrospective workflow for sessions that have had no activity for more than 24 hours. A retrospective is a review of what happened, what was missed, and what should change.

In plain words
What is it for?
Use it to find abandoned sessions, select a review depth based on their age, and record lessons or unfinished follow-up work.
Why use it?
It handles old sessions differently from recent ones, so stale context does not lead to an unnecessarily deep or costly review.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Codex.

Part of the second-brain-skills plugin — 248 skills, 1 plugin shipped together

not rated 9repo +1 changed 11d ago A scan 74 tokens original MIT

Good fit Use it to find abandoned sessions, select a review depth based on their age, and record lessons or unfinished follow-up work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tonydzi/second-brain-starter-kit/retro-lost
View source ↗ tonydzi/second-brain-starter-kit
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 tonydzi/second-brain-starter-kit --skill retro-lost
Clone the repo
git clone --depth 1 https://github.com/tonydzi/second-brain-starter-kit

Made for: Claude Code.

Or install second-brain-skills, the plugin that ships this one along with the rest of its 248 skills, 1 plugin.

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 retro-lost

README.md
[![agentmods](https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/retro-lost/github.svg)](https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/retro-lost)
Your own site
<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/retro-lost"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/retro-lost/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 retro-lost

Your own site · 80×15
<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/retro-lost"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/retro-lost.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,774 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 $0.00074 $0.07774
Opus 5.5 $0.00030 $0.03110
Sonnet 5.5 $0.00015 $0.01555
Haiku 4.5 $0.00007 $0.00777

Measured 11d ago against content hash 3be8b3044b47, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

retro-lost 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 11d 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.

skills/retro-lost/SKILL.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/retro-lost — ретро потерянных сессий

⭐ ОСЬ ВОЗРАСТА: когда сессия — потеряшка и какое ретро ей положено (anton 02.09.2026)

Потеряшка = сессия без касания >24 часов (было 5 дней; сканер retro_lost_scan.py, MIN_AGE_DAYS=1). Возраст решает ГЛУБИНУ ретро — поле retro_mode в строке кандидата:

  • 1–5 дней (classic) — контекст ещё тёплый, мир не успел далеко уйти → классическое качественное ретро: полный набор шагов профиля узла (см. таблицу профилей ниже), включая контрибьют-тест, тесты панелью и docstring-паспорта на хабе.
  • >5 дней (lite) — поезд ушёл (в другом или том же направлении — неважно, догонять дорого) → облегчённое ретро: шаги 0/0-бис/1/2/3/7/8, БЕЗ шагов 4/5/6/7-бис/9. RECALL при этом ПОЛНЫЙ — это не то, что режется (опасность №1 никуда не делась).

Ось возраста ⊥ оси профилей (хаб/пир): сначала возраст выбирает classic/lite, потом профиль узла режет своё. Итог = ПЕРЕСЕЧЕНИЕ (пир-лайт + classic всё равно без панели ломателей — она хабовая рельса; хаб + lite не делает панель даже при живой рельсе). MAX_AGE_DAYS=30 (амнистия) не тронут.

Чем отличается от живого /retro и почему

Сессия брошена дни назад: контекст холодный, автора нет, мир УШЁЛ ВПЕРЁД. Отсюда три сдвига:

  1. RECALL — главный шаг, а не разминка. Опасность №1 (Антон: «чтобы не суммаризировать старьё»): торжественно записать урок, который соседняя сессия уже записала, или судить артефакт, который с тех пор переписан/удалён. Каждый вывод сверяется с СЕГОДНЯШНИМ состоянием: память + MEMORY.md, grep волта, реестр задач, git log затронутых файлов ПОСЛЕ даты сессии. Урок уже записан → строка «уже в домах, дубль не создаю». Артефакт переписан позже → судим текущую версию, не сессионную.
  2. Часть живого ритуала НЕ нужна. Compact-блок Антону — некому жать. Growth-log — только если в сессии был реальный спор/решение. Биты дня — протухли (сюжетно ценное → черновик в content-mine, не в канон задним числом). Drift-audit с подъёмом дочерних сессий — только если RECALL доказал, что направление ещё живо и не подхвачено.
  3. Сессия не отвечает — все вердикты со степенью уверенности; «зачем это строили» без улики в транскрипте = 🤔 гипотеза, не факт.

Read the full file on GitHub · 281 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. 11d ago Changed · -1 lines 3be8b3044b47
  2. 14d ago Changed · +1 lines · -46 tokens per session e58895667c2b
  3. 16d ago Changed · +13 lines 5c21e7729a0c
  4. 25d ago First seen · 268 lines · 120 tokens per session scan A 6752335045f6

Subscribe to this mod's changes

retro-lost is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (9 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 7,774 once invoked, about $0.0003 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 2026-09-24.

Claude CodeProductivityProject managementai-agentsknowledge-managementobsidianpersonal-knowledge-managementsecond-brain
Related

Other skills, from other repositories

superbrain-distill

Internal SuperBrain skill — run by the detached capture child to distill a session-event delta into routed Obsidian notes. Not for direct user invocation.

m3talux/superbrain · 36 tokens

email-sorting

Customize and use a human-reviewed email sorting system for Gmail, Google Workspace, Outlook, Microsoft 365 or another connected mailbox. Use for first-time setup, folder or label recommendations from a read-only email sample, inbox triage, and applying approved sorting batches. Not for sending, replying to or…

AiAi-Mastermind/aiai-mastermind-tools-and-skills · 66 tokens

inbox

An inbox-management skill for scanning an LLM Wiki inbox, previewing pending files, choosing how to process them, and sending selected material through an import step.

johnfkoo951/cmds-llm-wiki · 43 tokens

canvas

Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.

AgriciDaniel/claude-obsidian · 72 tokens

pm

When you want to manage projects across your businesses using a kanban + Eisenhower methodology. One kanban per business (whatever portfolio of businesses, projects, or initiatives you run). Tool-agnostic — connects via API/MCP to whatever PM tool each business uses (Notion, GitHub Projects, Plane, Linear, Obsidian…

coreyhaines31/makerskills · 206 tokens

coach

Use when the user says /coach (today, week, month, profile, log), asks what to do today for training, asks for a workout, weekly training plan, or longevity plan, wants to log a finished workout or check lift progression (PR, plateau, deload), or a scheduled morning task fires to drop today's workout into the…

mycelium-hq/ai-brain-starter · 103 tokens