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 robrohan/claude-skills --skill stitchgit clone --depth 1 https://github.com/robrohan/claude-skillsWrote 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/robrohan/claude-skills/stitch)<a href="https://agentmods.dev/skills/robrohan/claude-skills/stitch"><img src="https://agentmods.dev/badge/skills/robrohan/claude-skills/stitch/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/robrohan/claude-skills/stitch"><img src="https://agentmods.dev/badge/skills/robrohan/claude-skills/stitch.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 | $0.00043 | $0.00710 |
| Opus 5.5 | $0.00017 | $0.00284 |
| Sonnet 5.5 | $0.00009 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
stitch scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The user wants to run stitch to extract e-reader highlights.
If arguments were provided ($ARGUMENTS), use them to infer the device type and/or output file. Otherwise, ask the user which device type they want (kobo or kindle) and whether they have an input path or want to rely on environment variables.
How to run stitch
stitch [-i input_file] [-o output_file.json] -t [kobo|kindle]
Options:
-t koboor-t kindle— required-i <path>— path to the input file (overrides env vars and defaults)-o <path>— output JSON file (defaults tokobo.jsonorkindle.json)
Typical input paths:
| OS | Device | Path |
|---|---|---|
| macOS | Kindle | /Volumes/Kindle/documents/My Clippings.txt |
| macOS | Kobo | /Volumes/KOBOeReader/.kobo/KoboReader.sqlite |
| Linux | Kindle | /media/$USER/Kindle/documents/My Clippings.txt |
| Linux | Kobo | /media/$USER/KOBOeReader/.kobo/KoboReader.sqlite |
Environment variables (set these to skip -i each time):
STITCH_KOBO— path to the Kobo SQLite fileSTITCH_KINDLE— path to the Kindle clippings file
Prerequisites
Before running stitch, make sure the binary is installed. If stitch is not found on the PATH, tell the user to download the appropriate binary for their platform from:
https://github.com/robrohan/stitch/releases
On macOS, after downloading, the user must right-click the binary in Finder and select "Open" once to bypass the unsigned binary warning before it can be used from the terminal.
Steps
- Check that
stitchis available by runningwhich stitch. If not found, stop and direct the user to download it from the releases page above. - Determine device type from
$ARGUMENTSor ask the user. - Determine input path: check if
STITCH_KOBO/STITCH_KINDLEis set, or ask the user for the path. - Run
stitch -t <type> [-i <input>] [-o <output>]using the Bash tool. - If successful, read back the output JSON with the Read tool and summarise:
- How many highlights were found
- How many unique books/titles
- Any annotations present
- Offer to filter or query the results further with
jq.
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.
- 2mo ago First seen · 59 lines · 43 tokens per session scan A 09712c11a05c
stitch is a skill published in the GitHub repository robrohan/claude-skills (1 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 710 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
offensive-vuln-classes
Exploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit…
model-prompt-pack
Use when asked to write prompts for image-to-3D or text-to-3D tools, generate 3D models of a topic's parts, plan the assets for a 3D explorer, or build a labelled parts list with sources. Produces prompts for image-to-3D tools, one per object, plus a parts list for labelling in which every label names a trusted…
explorer-interface-brief
Use when asked to design the interface for an interactive 3D explorer, plan a UI for exploring a 3D model of a topic, or write an image-model prompt for a 3D learning app mock-up. Produces, from a topic, the UI design brief (audience, layout, panels, interactions, label style, colour palette, accessibility) and an…
explorer-pipeline
Use when asked to make an interactive 3D explorer of a topic from start to finish, go from a topic to a clickable 3D learning page, or run the whole 3D explorer process. Produces a staged run of explorer-interface-brief, model-prompt-pack and explorer-viewer-builder in order for one topic, with the hand-offs between…
financial-statement-explainer
Explain a financial statement (P&L, balance sheet, or cash flow) in plain English. Use when asked to explain a P&L / income statement, a balance sheet, a cash flow statement, or to make financials understandable to a non-finance reader. Produces a plain-language walkthrough — what each section means, the line items…
get-more-from-ai
Level up how you actually use AI — from basic one-shot questions to the techniques that get dramatically better results — matched to what you already do. Use when asked how do I get better at using AI, how do power users use AI, I feel like I'm using AI at 10%, or teach me to use AI better. Produces an honest read of…