share-fix

share-fix is a skill for Claude Code from tonydzi/second-brain-starter-kit. It costs 78 tokens per session (7,629 once invoked), scanned A, original, MIT.

A workflow for sharing a fix with other people who may have the same problem. It searches GitHub for matching symptoms, identifies possible users, and prepares the fix for outreach.

In plain words
What is it for?
It is for turning a newly solved problem into a reusable result, finding affected repositories or developers, and recording whether sharing was completed or skipped.
Why use it?
A solution can remain isolated in one project even when others are experiencing the same issue. Searching the exact symptom helps find relevant recipients instead of scanning aimlessly.

Skill for Claude Code

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

Part of the second-brain-skills plugin — 246 skills shipped together

Good fit It is for turning a newly solved problem into a reusable result, finding affected repositories or developers, and recording whether sharing was completed or skipped.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tonydzi/second-brain-starter-kit/share-fix
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 share-fix
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 246 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 share-fix

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/share-fix"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/share-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,629 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 $0.00078 $0.07629
Opus 5.5 $0.00031 $0.03052
Sonnet 5.5 $0.00016 $0.01526
Haiku 4.5 $0.00008 $0.00763

Measured 7d ago against content hash 01ea1a228023, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

share-fix 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 7d 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/share-fix/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/share-fix — 🌍 починил у себя → сразу раздай миру

Канон: Библия reglament-pochinil-u-sebya-srazu-razday-miru + память fixed-it-share-it-with-the-world + CLAUDE.md §4.7. Логика Антона: в момент починки у нас в руках лучший поисковый ключ на свете — дословный симптом; никакой «робот-сканер всего GitHub» не сравнится с реверс-поиском того, кто только что дебажил. Поэтому раздача = ритуал в момент фикса, не фоновый сканер.

Шаг 0-бис — источник кандидатов: очередь (anton 01.09)

Кроме «только что починил в руках», кандидаты приходят из очереди $OBSIDIAN_VAULT/_outreach/share_fix_queue.jsonl — её наполняет /retro Step 4🌍 (судья), а раздаёт ночная рутина share-fix-daily (хаб, ≤3 pending за прогон, полный ритуал ниже на каждого; после раздачи строка кандидата дополняется status:done+threads). Формат строки: added·from·artifact·queries[дословные симптом-запросы]·numbers·status.

⛔ ТЕРМИНАЛЬНЫХ СТАТУСОВ ЧЕТЫРЕ, НЕ ОДИН (08.09.2026, 3-й датированный случай share-fix-selector-drift-task-vs-engine): раздача закрывает строку не только как done — ⚪ пусто кладётся как dry, ⛔ непереносимо как skip (VALID_STATUS движка). Селектор «status != done» поэтому поднимает УЖЕ отработанные строки: замер 08.09 — 40 «не-done», из них 17 закрыты вердиктом, и первые три FIFO были ровно такими. Открытая строка = статус НЕ в {done, dry, skip} И без даты done (строка вовсе без поля status, как писал casebook-drip, тоже открытая — наивный == pending её теряет).

⛔ ПРИПАРКОВАННУЮ СТРОКУ НЕ БЕРЁМ (замер 07.09, 1-й датированный случай ochered-ne-uvazhaet-pole-parkovki-revisit): строка может нести revisit: <дата> — это парковка до урожая, а не обычный pending, и ни текст рутины, ни share_fix_queue.py её не отличают. Перед взятием кандидата: revisit в будущем ⇒ пропустить, статус не трогать, взять следующий FIFO. Иначе в мир уезжают недоказанные числа (07.09 так чуть не ушёл A/B с n=1 за сутки до урожая). Популяцию очереди читай прибором (share_fix_queue.py status), а не числом из текста задачи — оно стареет молча (класс share-fix-selector-drift-task-vs-engine, 2 случая).

Read the full file on GitHub · 139 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. 7d ago Changed · +14 lines 01ea1a228023
  2. 11d ago Changed · -1 lines 8fb7e5910d9c
  3. 14d ago Changed · +1 lines · -85 tokens per session 394bc00504f6
  4. 16d ago First seen · 125 lines · 163 tokens per session scan A ced3d49353aa

Subscribe to this mod's changes

share-fix is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (9 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 7,629 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 2026-10-04.

Related

Other skills, from other repositories

wiki-lint

Run a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, provenance audit, or wiki audit. Reports graph, link, frontmatter, provenance-ledger, empty-section, and stale-index findings; it does not reason…

AgriciDaniel/claude-obsidian · 79 tokens

defuddle

Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.

AgriciDaniel/claude-obsidian · 57 tokens

wiki-fold

Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…

AgriciDaniel/claude-obsidian · 76 tokens

wiki-query

Answer an explicitly vault-scoped question from an Obsidian wiki without changing it. Use when the user selects the vault as the evidence source: query the wiki, query quick, query deep, explain from the wiki, summarize the vault, find in wiki, search the wiki, or based on the wiki. Do not route ordinary…

AgriciDaniel/claude-obsidian · 75 tokens

wiki-retrieve

Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…

AgriciDaniel/claude-obsidian · 81 tokens

wiki

Initialize, adopt, and route work for a separate Obsidian knowledge vault through the portable claude-obsidian core. Use for vault setup, scaffolding, workspace selection, cross-project configuration, or choosing the correct wiki sub-skill. Triggers: /wiki, set up wiki, scaffold vault, create knowledge base, adopt…

AgriciDaniel/claude-obsidian · 84 tokens