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.
npx skills add gpsaggese/helpers --skill slides.add_referencesgit clone --depth 1 https://github.com/gpsaggese/helpersWrote 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/gpsaggese/helpers/slides.add_references)<a href="https://agentmods.dev/skills/gpsaggese/helpers/slides.add_references"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/slides.add_references/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/gpsaggese/helpers/slides.add_references"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/slides.add_references.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 | $0.00010 | $0.00521 |
| Opus 5.5 | $0.00004 | $0.00208 |
| Sonnet 5.5 | $0.00002 | $0.00104 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade A, and why
slides.add_references 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.
What it actually says
Goal
- Review the passed slides file
<FILE>.smd, and add references to books and technical papers
Workflow
Find References
-
If
<FILE>already has references to technical papers, give them priority (e.g., in the* Referencesslide at the end) -
Do not add references as
//comments: add them to the* Referencesslide, following.claude/skills/slides.rules.md"References Slide" -
Add supporting references, following the source types and retrieval methods in
.claude/skills/references.rules.md# When Searching for References
Add Citations
-
Find text in
<FILE>that can take a citation, and add it -
Be sure the citation is correct. If unsure, do not add it
-
Citations:
- Are in the typst format (e.g.,
[@su2024dualformer]) - Correspond to entries in
refs.bibin the same dir as<FILE>
- Are in the typst format (e.g.,
Conventions
- Follow the role in
.claude/skills/role.ai_researcher.md - Follow the reference format and conventions in
.claude/skills/references.rules.md
Verification
- Check that each paper reference exists
- Make sure the document still runs, e.g.,
gen_slides.pyornotes_to_pdf.pywith--skip_action open_pdf. The goal is to confirm it runs, not to render it> gen_slides.py -i book.Agentic_AI/12.1 --notes_to_pdf_args="--skip_action open_pdf"- Too many references on one page (e.g., more than 4) can cause errors like:
which requires bisection to find the problematic referencewarning: layout did not converge within 5 attempts = hint: check if any states or queries are updating themselves error: cannot format citation in isolation ┌─ @preview/touying:0.7.4/src/magic.typ:175:8 │ 175 │ cite(it.key, form: "full") │ ^^^^^^^^^^^^^^^^^^^^^^^^^^ │ = hint: check whether this citation is measured without being inserted into the document
- Too many references on one page (e.g., more than 4) can cause errors like:
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 · 58 lines · 10 tokens per session scan A 22d09cce3be7
slides.add_references is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 10 tokens to every session and 521 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.
slides.add_references compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| slides.add_referencesgpsaggese/helpers | Skill | 158 | today | Apache-2.0 | A | 10 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |