corpus-ingest-core: Skill for Claude Code

.agents/skills/historical-episode-verified-report-path/SKILL.md

historical-episode-verified-report-path is a skill for Claude Code, Codex from norton77930/corpus-ingest-core. It costs 37 tokens per session (594 once invoked), scanned A, original, MIT.

A human-controlled workflow for moving one named historical podcast episode toward a verified research report.

In plain words
What is it for?
Use it when you have an exact podcast ID and episode reference and want to check coverage, review a suggested next step, or approve report publication.
Why use it?
It shows the next step and missing information, then requires approval before any report workflow is confirmed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is norton77930/corpus-ingest-core's own configuration. It tells Claude Code and Codex how to work on corpus-ingest-core itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything corpus-ingest-core configures →

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/historical-episode-verified-report-path/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.

agentmods badge for historical-episode-verified-report-path

README.md
[![agentmods](https://agentmods.dev/badge/skills/norton77930/corpus-ingest-core/historical-episode-verified-report-path/github.svg)](https://agentmods.dev/skills/norton77930/corpus-ingest-core/historical-episode-verified-report-path)
Your own site
<a href="https://agentmods.dev/skills/norton77930/corpus-ingest-core/historical-episode-verified-report-path"><img src="https://agentmods.dev/badge/skills/norton77930/corpus-ingest-core/historical-episode-verified-report-path/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 historical-episode-verified-report-path

Your own site · 80×15
<a href="https://agentmods.dev/skills/norton77930/corpus-ingest-core/historical-episode-verified-report-path"><img src="https://agentmods.dev/badge/skills/norton77930/corpus-ingest-core/historical-episode-verified-report-path.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 594 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 $0.00037 $0.00594
Opus 5 $0.00018 $0.00297
Sonnet 5 $0.00007 $0.00119
Haiku 4.5 $0.00004 $0.00059

Measured 12d ago against content hash add44b5cc007, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

historical-episode-verified-report-path 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 12d 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/historical-episode-verified-report-path/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Historical Episode Verified Report Path

Use this Skill when the user wants to advance one named historical episode (for example EP672) toward a verified research report. Do not use this Skill for latest-only flows (use the 017/018 Skills instead).

Protocol

  1. Ensure the operator has given an exact podcast_id and exact episode_ref. If they only want gaps, call query_verified_research_report_coverage with has_bundle=false once, present candidates, and wait for the human to pick one episode_ref. Do not auto-select.
  2. Call suggest_historical_verified_report_next_step once with that exact podcast_id and episode_ref. Explain the suggestion code, recommended tool (if any), missing/stale roles, and whether exact api_cost_ack will be required later.
  3. If suggestion is report_present, report digests and stop.
  4. If suggestion is publish_verified_report:
    • Call run_episode_verified_research_report_workflow with confirm=false and the same episode_ref.
    • Ask for and wait for a new explicit approval of that exact episode_ref.
    • Call the same tool exactly once with confirm=true.
    • Report once and stop.
  5. If suggestion is completion_action:
    • Call run_corpus_episode_completion_workflow with confirm=false, the canonical episode_ref, and action=next (or the suggested action only after re-preview matches).
    • Ask for and wait for explicit approval of the canonical episode and the exact selected executable action.
    • For semantic_summary, require the human to provide the exact acknowledgement text; do not invent it.
    • Call the completion tool exactly once with confirm=true and the approved action (and exact ack when required).
    • Report once and stop. Do not automatically call publish (019) in the same request.
  6. If suggestion is blocked, report missing/stale roles and stop.

Hard rules

  • One confirmed side-effect MCP call per user request, then stop.
  • Do not start another preview or confirm unless the user makes a new request.
  • Do not use CLI, terminal, retry, scheduler, autonomous loop, force, partial mode, batch, or automatic cache rebuild.
  • Do not resolve latest or substitute another episode.
  • Do not call 017/018 latest tools for this historical path.
  • Do not provide investment advice.
  • If MCP is unavailable, report a setup problem only.

Read the full file on GitHub · 53 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. 12d ago First seen · 53 lines · 37 tokens per session scan A add44b5cc007

Subscribe to this mod's changes

historical-episode-verified-report-path is a skill published in the GitHub repository norton77930/corpus-ingest-core (2 stars, last pushed 12d ago), licensed MIT. It adds 37 tokens to every session and 594 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

openkb-deck-neon

A skill for creating a single-file HTML slide deck from content stored in OpenKB, a knowledge-base chat system. It defines a dark, high-tech visual style using neon colors, glow effects, and glass-like panels.

VectifyAI/OpenKB · 173 tokens

openkb-deck-editorial

A tool for creating a single-file HTML slide presentation from compiled knowledge-base content. Its visual style uses a warm cream background, serif typography, and brick-red accents.

VectifyAI/OpenKB · 117 tokens

openkb-html-critic

Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…

VectifyAI/OpenKB · 132 tokens

karpathy-llm-wiki

Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.

Astro-Han/karpathy-llm-wiki · 67 tokens

transformer-attention

Use when reasoning about Transformer self-attention, multi-head attention, positional encoding, masked decoder attention, or why attention replaced recurrence/convolutions in sequence models; not for generic NLP or unrelated attention topics.

VectifyAI/OpenKB · 46 tokens

release-sync

Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.

yonatangross/orchestkit · 62 tokens