What is workflow-derivation-bundle?

A tool for deriving a workflow from one named podcast episode with an existing lecture and a configured workflow context. It previews the derivation before it is generated or reused.

Use it to preview, generate, or reuse a workflow based on a specific podcast lecture.

It prevents a workflow from being made for an ambiguous or incorrect episode and requires approval before execution. It also keeps lecture creation and workflow derivation as separate requests.

How norton77930/corpus-ingest-core configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to norton77930/corpus-ingest-core. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/norton77930/corpus-ingest-core/main/.agents/skills/workflow-derivation-bundle/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/norton77930/corpus-ingest-core

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/norton77930/corpus-ingest-core/workflow-derivation-bundle/github.svg)](https://agentmods.dev/skills/norton77930/corpus-ingest-core/workflow-derivation-bundle)

Your own site

<a href="https://agentmods.dev/skills/norton77930/corpus-ingest-core/workflow-derivation-bundle"><img src="https://agentmods.dev/badge/skills/norton77930/corpus-ingest-core/workflow-derivation-bundle/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/norton77930/corpus-ingest-core/workflow-derivation-bundle"><img src="https://agentmods.dev/badge/skills/norton77930/corpus-ingest-core/workflow-derivation-bundle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,772 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.

Model	Per session	Once invoked
Fable 5.1	$0.00019	$0.01772
Opus 5.5	$0.00008	$0.00709
Sonnet 5.5	$0.00004	$0.00354
Haiku 4.5	$0.00002	$0.00177

Measured 29d ago against content hash 72475e698f79, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

workflow-derivation-bundle 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 29d 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/workflow-derivation-bundle/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow Derivation Bundle

Use for one named episode with an existing lecture and the configured default workflow context. The only callable tool is derive_workflow_bundle.

P01 Target

Require explicit podcast_id and episode_ref and one operation. A combined lecture/derivation request must first be narrowed to one operation. Missing/ambiguous IDs or URLs require clarification before any call. Reject empty, whitespace-padded or separator-containing identifiers and case-insensitive latest/next. Preserve valid underscores and case. Do not normalize, discover or invent identifiers.

Default force=false. Use true only for an explicit replacement request before preview and include it in approval. User-reported recovery trouble means stop for manual review, not a repair attempt.

P02 Preview

Call the bound tool once with exact IDs, confirm=false, requested force and api_cost_ack="". Initial invocation is not execution approval. This is the only preview in the cycle; no filesystem inspection or alternate tool lookup.

P03 Validate

Require ok=true, dry_run=true, requires_confirmation=true, network_read=false, not_investment_advice=true, run_mode="preview", matching tool name and exact inputs podcast_id/episode_ref/force. Require reads/writes/reuses/metadata_writes/warnings/risks to be lists of strings. There is no requires_llm or report_writes field in this contract. Missing fields, wrong types, identity mismatch or contradictory roles mean incompatible preview: stop without confirm.

Compare final filename and parent with either slash style, without resolving/opening paths. Require distinct sibling paths with exactly 05_prompt_examples.md and 06_apply_to_my_workflow.md. Reject duplicates, extra/missing roles or mixed directories. Use only these combinations:

Branch	writes roles	reuses roles	LLM
generate	05,06	none	yes
reuse	none	05,06	no

Require metadata_writes as a separate list of strings: generation requires one distinct sibling workflow_derivation.lineage.json path with the same parent as05/06; reuse requires an empty list. Missing metadata_writes, wrong names, mixed parents, duplicates or contradictory metadata stop without confirm. Older backend previews lacking this field are incompatible.

Read the full file on GitHub · 93 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.

29d ago First seen · 93 lines · 19 tokens per session scan A 72475e698f79

Subscribe to this mod's changes

workflow-derivation-bundle is a skill published in the GitHub repository norton77930/corpus-ingest-core (2 stars, last pushed 29d ago), licensed MIT. It adds 19 tokens to every session and 1,772 once invoked, about $0.0001 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 2026-10-08.

LLM Learning and teaching Planning ai-agents knowledge-base mcp

workflow-derivation-bundle next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
workflow-derivation-bundlenorton77930/corpus-ingest-core	Skill	2	29d ago	MIT	A	19	Claude Code, Codex
paper-readerpoco-ai/Agentero	Skill	1.1k	yesterday	MIT	A	43	Claude Code, Codex
transformer-attentionVectifyAI/OpenKB	Skill	4.9k	3mo ago	Apache-2.0	A	46	Claude Code, Codex
asa-reader-layer-writer3yesore/LetUenforskills	Skill	2	4mo ago	MIT	A	27	Claude Code, Codex
canvasNousResearch/hermes-agent	Skill	261k	yesterday	MIT	A	12	Claude Code, Codex
playwrightopenai/openai-agents-python	Skill	31k	yesterday	MIT	A	19	Claude Code, Codex
show-mehumanlayer/humanlayer	Skill	13k	yesterday	Apache-2.0	A	25	Claude Code

corpus-ingest-core: Skill for Claude Code