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 stevepridemore/graph-memory --skill plain-tech-docsgit clone --depth 1 https://github.com/stevepridemore/graph-memoryWrote 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/stevepridemore/graph-memory/plain-tech-docs)<a href="https://agentmods.dev/skills/stevepridemore/graph-memory/plain-tech-docs"><img src="https://agentmods.dev/badge/skills/stevepridemore/graph-memory/plain-tech-docs/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/stevepridemore/graph-memory/plain-tech-docs"><img src="https://agentmods.dev/badge/skills/stevepridemore/graph-memory/plain-tech-docs.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 | $0.00000 | $0.00674 |
| Opus 5.5 | $0.00000 | $0.00270 |
| Sonnet 5.5 | $0.00000 | $0.00135 |
| Haiku 4.5 | $0.00000 | $0.00067 |
Grade A, and why
plain-tech-docs 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 9d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The user wants technical documentation that sounds like an experienced engineer wrote it: plain words, short sentences, no marketing voice.
Arguments: $ARGUMENTS
Steps
-
Run the checker on the paths given (default: every
*.mdin the current repo):python3 ~/.claude/skills/plain-tech-docs/scripts/check_docs.py <paths>It prints
file:line:col: [category] "match" -> suggestionand a summary. It skips fenced and inline code, link targets, HTML comments and front matter. Exit status 1 means it found something. -
Read each finding in context before changing anything. The list is a prompt, not a rule: "just" in "just one flag" is fine, "robust" can be the right word in a statistics doc, and a long sentence inside a numbered step may be clearer than two. Leave correct uses alone.
-
When you rewrite, follow the rules below. Change prose only; never touch commands, code, config keys, version numbers, or link targets.
-
Re-run the checker and report what changed and what you left on purpose.
Rules for the prose
- Say what the thing does. Replace "robust", "powerful", "seamless" with the concrete behavior ("retries three times", "restarts on crash").
- Use the short word: use, help, start, many, to. See
references/word-list.mdfor the full list. - One idea per sentence. Aim for under 25 words; the checker flags over 35.
- Cut throat-clearing: "It's worth noting", "In today's", "Let's dive in", "In conclusion". Start with the point.
- No em-dashes. Use a comma, colon, parentheses, or a new sentence.
- No exclamation marks in technical prose.
- Don't hedge with "simply", "easily", "basically". If a step is easy the reader will notice.
- Runbooks: imperative steps ("Restart the service"), one action per step, expected output after the command, and what to do if it differs.
- Keep the author's facts, structure and headings. This is an edit, not a rewrite.
Tuning
- Skip a category:
--ignore hedge(repeatable). Categories are the##headings in the word list pluslong-sentence. - Change the sentence limit:
--max-words 40, or0to turn it off. - Machine-readable output:
--format json. - Add or remove patterns by editing
references/word-list.md. A bullet that starts withre:is a regular expression.
What ships with it
2 files 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.
- 9d ago First seen · 61 lines · 0 tokens per session scan A 8f44b63e40b1
plain-tech-docs is a skill published in the GitHub repository stevepridemore/graph-memory (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 674 tokens. 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 2026-10-19.
Other skills, from other repositories
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
crystalline-presentation
Use when writing or updating a reflection or PACT.md, working reflect feedback, update or review items, or writing an engram that a table, diagram or callout would make easier to find or use. Messages between parties need a sequenceDiagram, a process with a branch a flowchart, states a stateDiagram-v2, three or more…
install-waggle
Install the official Waggle plugin locally for Codex from the latest stable Abhigyan-Shekhar/Waggle-mcp GitHub Release. Use for explicit requests such as "Install Waggle", "Set up Waggle", "Install Waggle for Codex", or "Enable Waggle". Do not use for Waggle operation, repair, updates, configuration, or memory…
example-skill
Example module showing the format. Use when: testing /enable-modules, learning to author a module.
slm-media
Save pictures and PDFs in SuperLocalMemory and find them again by describing them. Covers when to save a picture or document, remembermedia, rememberdocument, getmedia, mediastatus and mediauploadlink, how recall returns pictures and PDF pages, the limits, what stays private, turning the feature on with slm media (16…
goodmem:mcp
Workflow guide for GoodMem MCP server tools. Use when an agent needs to understand what GoodMem MCP tools are available and how to use them. Parameter signatures are provided by the MCP protocol itself — do not hardcode them here.