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 agentmods add instructions/glukicov/slideops/claude-mdgit clone --depth 1 https://github.com/glukicov/slideopsWrote 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/instructions/glukicov/slideops/claude-md)<a href="https://agentmods.dev/instructions/glukicov/slideops/claude-md"><img src="https://agentmods.dev/badge/instructions/glukicov/slideops/claude-md.svg" alt="Measured on agentmods" 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 | $0.01321 | $0.01321 |
| Opus 5 | $0.00660 | $0.00660 |
| Sonnet 5 | $0.00264 | $0.00264 |
| Haiku 4.5 | $0.00132 | $0.00132 |
Grade A, and why
slideops CLAUDE.md 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 5d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this repository is
SlideOps is not an application: it is two Agent Skills (markdown + two Python scripts) that get installed onto other people's machines, plus the development harness that proves they work. Almost every rule below follows from that split:
skills/slideops/andskills/slides-to-pdf/— shipped. Standard library only.scripts/,tests/,pyproject.toml— development harness. Never installed, free to use third-party deps (typer,pypdfium2,Pillow).
The repo is also its own Claude Code plugin marketplace (.claude-plugin/), so the same
tree is both the source and the distribution channel.
Commands
uv sync --dev # setup; uv fetches Python 3.14 from .python-version
uv run ruff check . # lint
uv run ruff format --check . # format
uv run ty check # types — this repo uses ty, NOT mypy
uv run pytest # unit + freshness end-to-end tests
uv run python scripts/validate.py # frontmatter, template invariants, manifest versions
uv run python scripts/smoke_test.py # render every slide, export and verify a PDF (needs Chromium)
Single test: uv run pytest tests/test_freshness.py::test_a_deleted_file_reports_missing.
CI runs all of the above plus two guards that are easy to trip locally:
# the demo deck's citations must still match this repo
uv run python skills/slideops/scripts/check.py skills/slideops/examples/skill-demo.html --repo .
# the shipped scripts must run on bare python3 with nothing installed
python3 skills/slideops/scripts/check.py skills/slideops/examples/skill-demo.html --repo .
uv run pre-commit install wires ruff, ty, pytest and validate.py into every commit.
The citation mechanism (the core idea)
A deck is a single self-contained HTML file. Every quoted snippet carries
data-src="path/file.py:40-58" and data-sha256="<12 hex>", and the <head> carries
<meta name="slideops-build" content="commit=… date=… repo=…">. Those two facts are what
make a generated document checkable later:
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.
- 5d ago First seen · 101 lines · 1,321 tokens per session scan A 78f07f71ccac
slideops CLAUDE.md is an instructions file published in the GitHub repository glukicov/slideops (36 stars, last pushed 2d ago), licensed MIT. It adds 1,321 tokens to every session, about $0.0066 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.
Other instructions, from other repositories
Skill_Seekers CLAUDE.md
Instructions for yusufkaraaslan/Skill_Seekers, covering claude.md, project overview, essential commands, required before running tests or cli (src/ layout) and run all tests (never skip - all must pass before commits).
Skill_Seekers AGENTS.md
Instructions for yusufkaraaslan/Skill_Seekers, covering agents.md - skill seekers, project overview, key capabilities, setup and with dev tools (pytest, ruff, mypy, coverage).
han CLAUDE.md
Claude Code instructions for testdouble/han, covering han: project map, creating skills, agents, or other plugin aspects, repository layout, when to use which doc and entry points.
trigger_tree CLAUDE.md
Claude Code instructions for Hedde/trigger_tree: Keep this file as a router. Read only the references needed for the task.
sourcebook CLAUDE.md
Instructions for BackendGameSetMatch/sourcebook, covering ai documentation, when to consult docs, how to access, keep docs alive and hard rules from conventions.
SeekMoney-ai CLAUDE.md
Claude Code instructions for zykooooooooo/SeekMoney-ai, covering claude.md, project overview, development commands, development and production.