agentmods.dev

ingest-source

A workflow for adding new documents, scans, tables, chat extracts, and business information to a local knowledge system while keeping the original material unchanged.

In plain words
What is it for?
Use it to classify incoming material, convert it to Markdown, check large source documents, and place it in the correct raw, agent, project, or output area.
Why use it?
It prevents source information from being mixed with derived notes, temporary outputs, or existing knowledge without a clear place.

Skill for Claude CodeCodex

11 2mo ago A scan 79 tokens original MIT
View the source file TheMuleA/codex-agent-core-template
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.

agentmods
npx agentmods add skills/themulea/codex-agent-core-template/ingest-source
Any agent
npx skills add TheMuleA/codex-agent-core-template --skill ingest-source
Clone the repo
git clone --depth 1 https://github.com/TheMuleA/codex-agent-core-template

Made for: Claude Code, Codex.

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,530 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00079 $0.01530
Opus 5 $0.00039 $0.00765
Sonnet 5 $0.00016 $0.00306
Haiku 4.5 $0.00008 $0.00153

Measured 2d ago against content hash 2ddc109553bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ingest-source 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 2d 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.

.agents/skills/ingest-source/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ingest-source

Назначение

Помогает безопасно принять новый материал в локальную knowledge system без потери исходного смысла, без подмены источника и без самовольного изменения существующих файлов.

Когда использовать

  • Пользователь передал документ, текст, PDF-конвертацию, PNG-сканы, таблицу, изображение или фрагмент чата.
  • Пользователь просит добавить данные о компании, продуктах, конкурентах, CRM, продажах, рынке, менеджерах или процессах.
  • Нужно решить, является ли материал raw-источником, знанием Agent Core, проектным знанием, planning/work item или временным output.
  • Нужно выполнить Markdown-оцифровку, сверку или аудит большого source-документа из raw/.

Scope routing

Перед ingest определить scope:

  • raw — первичный источник, оригинал, конвертация, OCR, выгрузка, скан, таблица или raw-derived Markdown.
  • agent — правила и знания Agent Core: протоколы, архитектура, boot, skills, safety, provenance, linking, planning, lint.
  • project:<project_id> — бизнес-данные выбранного project layer.
  • output — временный черновик, отчёт или промежуточный результат.

Фактический project_id берётся из projects/index.md после выбора active project.

References

Открывай reference-файлы только когда они реально нужны:

  • references/source-folder-structure.md — если нужно предложить структуру raw/sources/<source-name>/ или решить, какие source-папки создавать.
  • references/source-reports.md — если нужен key takeaways gate, source impact report или source card.
  • references/raw-document-processing.md — если работаешь с PDF, PNG-сканами, OCR, raw-derived Markdown, большой Markdown-оцифровкой, отдельным source-notes.md, структурными комментариями или аудитом переноса.

Общая процедура

  1. Определи тип материала: источник, факт, событие, решение, принцип, черновик, справочная заметка или задача.
  2. Определи scope: raw, agent, project:<project_id> или output.
  3. Предложи место хранения: raw/, agent/, projects/<project_id>/, agent/planning.md, project pending/roadmaps/work plans или output/.
  4. Объясни, почему выбран этот путь.
  5. Для значимого источника подготовь key takeaways gate перед предложением переноса в Agent Core, project layer, roadmaps или pending items; формат смотри в references/source-reports.md.
  6. Определи, какие существующие Agent Core или active project pages могут быть затронуты.
  7. Для значимого источника после чтения, расшифровки или аудита подготовь source impact report; формат смотри в references/source-reports.md.
  8. Предложи источники и уровень уверенности по agent/protocols/provenance-policy.md.
  9. Если нужен source card, сначала выбери место по agent/protocols/provenance-policy.md: существующая Markdown-расшифровка, raw-derived index.md, связанная рабочая page, project documents.md или отдельный source-notes.md.
  10. Предложи необходимые внутренние ссылки по agent/protocols/linking-policy.md.
  11. Если будет создана или обновлена page, используй agent/protocols/page-conventions.md.
  12. Сформируй предложение изменения через propose-file-change.
  13. Не изменяй файлы без подтверждения пользователя.
  14. После подтверждения применяй только согласованные изменения через safe-apply-change.
  15. Обнови релевантные индексы и logs.

Read the full file on GitHub · 90 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 90 lines · 79 tokens per session scan A 2ddc109553bc

Subscribe to this mod's changes

ingest-source is a skill published in the GitHub repository TheMuleA/codex-agent-core-template (11 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 1,530 once invoked, about $0.0004 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 2026-08-30.

DocumentsProductivity
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens