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.
curl -O https://raw.githubusercontent.com/norton77930/corpus-ingest-core/main/.agents/skills/learning-workflow-advance/SKILL.mdgit clone --depth 1 https://github.com/norton77930/corpus-ingest-coreWrote 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/norton77930/corpus-ingest-core/learning-workflow-advance)<a href="https://agentmods.dev/skills/norton77930/corpus-ingest-core/learning-workflow-advance"><img src="https://agentmods.dev/badge/skills/norton77930/corpus-ingest-core/learning-workflow-advance/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.
<a href="https://agentmods.dev/skills/norton77930/corpus-ingest-core/learning-workflow-advance"><img src="https://agentmods.dev/badge/skills/norton77930/corpus-ingest-core/learning-workflow-advance.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00018 | $0.00899 |
| Opus 5.5 | $0.00007 | $0.00360 |
| Sonnet 5.5 | $0.00004 | $0.00180 |
| Haiku 4.5 | $0.00002 | $0.00090 |
Grade A, and why
learning-workflow-advance 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learning Workflow Advance
Use when the operator asks for the next learning step for one named episode. Only callable tool: advance_learning_workflow. Existing separate Skills still serve explicitly selected lecture/derivation operations. Batch, full-chain, repair, replacement/force and upstream preparation requests need narrowing to one supported step before any call.
Target and preview
Require explicit podcast_id and episode_ref. Clarify missing/ambiguous IDs; reject latest/next, URLs, padding, separators and unsafe IDs before calls. Preserve valid case/underscores; do not normalize, discover or invent IDs. Missing mounted tool means setup trouble: stop.
Call one preview with matching IDs, confirm=false, expected_action="", expected_plan_id="", api_cost_ack="". The initial request is not execution approval. Read the response contract before validating responses; this is instruction loading, not corpus inspection. Use the actual Tool32 envelope, not the separate generation tools' schemas.
Validate identity, types, scoped state, action/cost combination and owned plan roles using that reference. Invalid/unknown/contradictory responses stop without confirm. complete means scoped reusable bundles; report and stop, no report-only confirmation. blocked means manual review; explain only known diagnostics and stop. Neither state asks for execution approval.
Explain and obtain consent
For action_available, show target, next action, fixed read roles, writes/reuses, metadata_writes, report_writes, costs and known warnings before approval. Lecture generation sends the existing semantic summary; derivation sends lecture content and default workflow context. This workflow does not send raw transcript text. Cover completion calls no LLM but writes its cover and run reports.
Explain that plan_id binds metadata only, not source bytes, authentication or a lock. Observations are non-atomic; writers must be serialized. Scoped currentness is not summary-to-transcript freshness or content-quality proof; cache rebuild stays manual.
What ships with it
1 file 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.
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 · 38 lines · 18 tokens per session scan A 342cacb6480d
learning-workflow-advance is a skill published in the GitHub repository norton77930/corpus-ingest-core (2 stars, last pushed 29d ago), licensed MIT. It adds 18 tokens to every session and 899 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.
learning-workflow-advance compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| learning-workflow-advancenorton77930/corpus-ingest-core | Skill | 2 | 29d ago | MIT | A | 18 | Claude Code, Codex |
| paper-readerpoco-ai/Agentero | Skill | 1.1k | yesterday | MIT | A | 43 | Claude Code, Codex |
| job-interview-coachingmagnus919/agent-skills | Skill | 166 | 2d ago | MIT | A | 84 | Claude Code, Codex |
| transformer-attentionVectifyAI/OpenKB | Skill | 4.9k | 3mo ago | Apache-2.0 | A | 46 | Claude Code, Codex |
| sales-setupBevel-Software/Hexis | Skill | 123 | yesterday | Apache-2.0 | B | 109 | Claude Code, Codex |
| call-prepBevel-Software/Hexis | Skill | 123 | yesterday | Apache-2.0 | B | 84 | Claude Code, Codex |
| end-of-dayBevel-Software/Hexis | Skill | 123 | yesterday | Apache-2.0 | B | 75 | Claude Code, Codex |