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/carloshpdoc/ios-workflow-claude/knowledgenpx skills add carloshpdoc/ios-workflow-claude --skill knowledgegit clone --depth 1 https://github.com/carloshpdoc/ios-workflow-claudeWrote 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/carloshpdoc/ios-workflow-claude/knowledge)<a href="https://agentmods.dev/skills/carloshpdoc/ios-workflow-claude/knowledge"><img src="https://agentmods.dev/badge/skills/carloshpdoc/ios-workflow-claude/knowledge.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 | $0.00000 | $0.02425 |
| Opus 5 | $0.00000 | $0.01213 |
| Sonnet 5 | $0.00000 | $0.00485 |
| Haiku 4.5 | $0.00000 | $0.00243 |
Grade A, and why
knowledge 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/knowledge — federa busca + lifecycle em docs .md
Voce eh um "bibliotecario" pros docs .md do usuario. Tres fontes:
~/Desktop/knowledge/— cross-cutting docs (ideias, playbooks, audits, learnings)- Repo do projeto atual —
find . -name "*.md" -not -path "*/node_modules/*"(cwd atual) - Memory do Claude —
~/.claude/projects/<projeto>/memory/se aplicavel
Subcomandos
$1 define o que fazer. Se vazio, default eh index.
/knowledge index (default)
Imprime visao organizada de tudo. Format:
Knowledge base summary
======================
CENTRAL (~/Desktop/knowledge/)
- ideas/ (N docs, X stale)
- playbooks/ (N docs)
- audits/ (N docs, X stale)
- learnings/ (N docs)
- archive/ (N docs)
PROJECT (cwd)
- doc1.md (last_review: 2026-05-17, status: active)
- doc2.md (last_review: 2026-04-12, STALE)
...
MEMORY (~/.claude/projects/.../memory)
- memory1.md (type: feedback)
- memory2.md (type: project)
CONTENT DRAFTS
- 2026-05-17-claude-mcp-bigquery-ga4/ (4 platforms, status: drafted)
- ...
Format limpo, ordenado, status visiveis. Maximo ~50 linhas — se passar, agrupa por tag.
/knowledge stale [days]
Lista docs onde last_review > N dias atras (default 60).
Para cada .md em todas as fontes:
- Le frontmatter, extrai
last_review(ou usa file mtime se frontmatter ausente) - Calcula dias desde ultima review
- Se > threshold, inclui na lista
- Ordena por staleness (mais velho primeiro)
Output:
Docs stale (last_review > 60 dias):
1. ~/Desktop/knowledge/audits/ga4-audit-2025-q4.md
last_review: 2025-11-20 (178 dias atras)
tags: [analytics, ga4]
sugestao: re-validar com dado atual ou archive
2. /Users/.../mysite/PORTFOLIO_STRUCTURE_RESEARCH.md
last_review: ausente, mtime: 2026-02-10 (96 dias atras)
sugestao: adicionar frontmatter ou archive
/knowledge drafts
Lista content drafts nao publicados.
Scaneia <project>/content/drafts/ no repo atual. Pra cada subdir:
- Le os 4 .md (linkedin/twitter/instagram/article)
- Checa se tem checklist
[x]indicando posted ou se ainda esta[ ] - Lista grouped por status
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 · 262 lines · 0 tokens per session scan A 6c9e0835c910
knowledge is a skill published in the GitHub repository carloshpdoc/ios-workflow-claude (7 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,425 tokens. 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
llm-wiki
Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or…
alive:save
The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…
alive:capture-context
Use when external content arrives in the session — emails, transcripts, screenshots, documents, files, or in-session research worth keeping. Also use when there's nothing obvious to capture — the skill checks 03Inbox/ for unrouted files and enters inbox scan mode. Stores raw content, routes to bundles, extracts tasks…
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:load-context
The human mentions a walnut to work on, asks about a specific venture/experiment/project, or wants to check status — not just explicit 'load X'. Load the brief pack (3 files), resolve the people involved, check the active bundle — then surface one observation and ask what to work on. Context loads in tiers: walnut and…
alive:mine-for-context
Deep context extraction from source material. Creates reference bundles, builds extraction plans, tracks what's been extracted, and discovers new targets — people, subjects, patterns, connections. The archaeologist that turns raw sources into structured knowledge. Can be invoked by alive:session-history for targeted…