What is slides.update_from_source?

A slide updater that follows source citations from one slide file to the files and lines they came from. It finds source changes and applies the relevant updates to the citing slides.

Use it to keep source-backed slides current after editing the original slides or documents.

It reduces the risk that slides become inconsistent with the source material they quote or reference. An optional title or line range limits the work to part of the deck.

slides.update_from_source — Skill for Claude Code by gpsaggese/helpers

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.

Any agent

npx skills add gpsaggese/helpers --skill slides.update_from_source

Clone the repo

git clone --depth 1 https://github.com/gpsaggese/helpers

Made for: Claude Code.

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/gpsaggese/helpers/slides.update_from_source/github.svg)](https://agentmods.dev/skills/gpsaggese/helpers/slides.update_from_source)

Your own site

<a href="https://agentmods.dev/skills/gpsaggese/helpers/slides.update_from_source"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/slides.update_from_source/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/gpsaggese/helpers/slides.update_from_source"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/slides.update_from_source.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,741 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	$0.00011	$0.01741
Opus 5.5	$0.00004	$0.00696
Sonnet 5.5	$0.00002	$0.00348
Haiku 4.5	$0.00001	$0.00174

Measured yesterday against content hash ee98cb4f2063, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

slides.update_from_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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

slides.update_from_source — 92% identical, 46 lines differ

.claude/skills/slides.update_from_source/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal

Given a slides file <TARGET> (.smd) whose slides cite their source slides with // From: <SOURCE>:<LINE> '<source line>' comments, find what changed in each <SOURCE> and incorporate it into the citing slide of <TARGET>
Optionally, the user passes a scope (a slide title or a line range in <TARGET>). Then process only the slides in that scope

Workflow

Read the conventions in .claude/skills/slides.rules.md, especially ## Source Attribution (// From: ...)

List the Citations

Extract every // From: line of <TARGET> with its line number
```
> grep -n "^// From:" <TARGET>
```
Attach each citation to the nearest preceding * <slide title> line
Skip a bare // From: ... (nothing after the colon). It marks a slide with no identified source. Do not guess a source and do not drop the line
Group the citations by <SOURCE> file, so each <SOURCE> is read once

Resolve Each Source Slide

Check that <SOURCE> exists. If it does not, report it and go to the next citation
Find the current position of the cited line in <SOURCE>
- Search for the verbatim '<source line>' text, including its leading marker (* , #, ## , ### ). <LINE> drifts whenever <SOURCE> is edited above it
```
> grep -nF -- '<source line>' <SOURCE>
```
- If several lines match, pick the one closest to the recorded <LINE>
- If nothing matches, the source slide was renamed, moved, or deleted
  - Search for the title text without its marker, and for a close variant
  - If a single clear candidate exists, use it and record the new text in the // From: line
  - If no candidate exists, report "source missing", leave the slide and its // From: line unchanged, and go to the next citation
Extract the source content
- For a * <slide title> line: the lines up to the next * slide or # header line
- For a #, ##, ### header line: the lines up to the next header of the same or higher level. Only the part matching the citing slide's topic is relevant
- For a - [P<NNN>] or - [B<NNN>] entry in related_papers.md or related_books.md: the entry itself. Compare only its text (authors, title, year, link) with the reference used in the slide

Read the full file on GitHub · 147 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.

yesterday First seen · 147 lines · 11 tokens per session scan A ee98cb4f2063

Subscribe to this mod's changes

slides.update_from_source is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 11 tokens to every session and 1,741 once invoked, about $0.0000 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 2026-11-06.

Documents Writing and docs

slides.update_from_source next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
slides.update_from_sourcegpsaggese/helpers	Skill	158	today	Apache-2.0	A	11	Claude Code
orbit-notionnexu-io/open-design	Skill	106k	today	Apache-2.0	A	117	Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-plugins	Skill	35k	today	Apache-2.0	A	123	Claude Code
apify-youtube-transcript-scrapersickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	48	Claude Code
legal-holdanthropics/claude-for-legal	Skill	9.9k	today	Apache-2.0	A	68	Claude Code
report-to-pdfasgeirtj/system_prompts_leaks	Skill	71k	today	CC0-1.0	A	17	Claude Code, Codex
artifact-template-minimal-letterheadasgeirtj/system_prompts_leaks	Skill	71k	today	CC0-1.0	A	54	Claude Code, Codex