Borrowing it
Nothing to install: this file belongs to degiz/kobo2calibre. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/degiz/kobo2calibre/main/.agents/skills/debug-highlights/SKILL.mdgit clone --depth 1 https://github.com/degiz/kobo2calibreWrote 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/degiz/kobo2calibre/debug-highlights)<a href="https://agentmods.dev/skills/degiz/kobo2calibre/debug-highlights"><img src="https://agentmods.dev/badge/skills/degiz/kobo2calibre/debug-highlights.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 | $0.00017 | $0.01326 |
| Opus 5 | $0.00009 | $0.00663 |
| Sonnet 5 | $0.00003 | $0.00265 |
| Haiku 4.5 | $0.00002 | $0.00133 |
Grade A, and why
debug-highlights 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 7d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Highlights Skill
Debug CFI conversion issues by creating manual ground-truth highlights in both systems and comparing converter output.
Config
Read paths.kobo_db and paths.calibre_db from .agents/config.yaml. If the file is missing, ask the user for paths and create it.
- Defaults: Kobo
KoboReader.sqliteon mounted volume, Calibremetadata.dbin library dir - Logs:
.agents/logs/debug-highlights-<timestamp>.log - Kepub: Always
newformat, max verbosity (-vv)
Workflow
WARNING: Deletes all highlights for selected book (preserved in memory, but lost if skill crashes). User should have backups.
IMPORTANT Kobo and Calibre use different versions of the same book: Calibre has a original epub, while Kobo has a kepubified version. The source code of "kepubify" is available in "kepubify.py". If needed, lookup other source code of Calibre.
IMPORTANT Calibre's CFI encode/decode logic lives in cfi.pyj: https://raw.githubusercontent.com/kovidgoyal/calibre/master/src/pyj/read_book/cfi.pyj — key functions: encode(), adjust_node_for_text_offset(), decode(), node_for_text_offset().
IMPORTANT Calibre's kepubify logic (adds kobo spans to EPUB HTML): https://raw.githubusercontent.com/kovidgoyal/calibre/master/src/calibre/ebooks/oeb/polish/kepubify.py — local copy in kepubify.py. Key function: kepubify_html_data().
IMPORTANT Always run calibre-customize -b $(pwd) before calibre-debug -e. The dual import loads the installed plugin, not local files. Symptom of staleness: debug logging you added doesn't appear.
Phase 1: Identify Book
- Verify Kobo mounted:
test -f /Volumes/KOBOeReader/.kobo/KoboReader.sqlite - Ask user for book name
- Query:
SELECT DISTINCT VolumeID, COUNT(*) FROM Bookmark WHERE VolumeID LIKE '%?%' AND text != '' GROUP BY VolumeID - User confirms which VolumeID
Phase 2.5: Ground Truth Setup
- User selects 1 highlight to test
- Preserve all highlights to memory (both DBs)
- Delete all existing highlights, including those marked as "removed":
DELETE FROM Bookmark WHERE VolumeID = ?andDELETE FROM annotations WHERE book = ? - User creates same highlight manually on Kobo device (unmount, highlight, remount)
- Verify:
SELECT * FROM Bookmark WHERE VolumeID = ? ORDER BY DateCreated DESC LIMIT 1 - User creates same highlight manually in Calibre viewer (must close viewer to save)
- Verify:
SELECT annot_data FROM annotations WHERE book = ? LIMIT 1 - Display both ground truth highlights side-by-side
- User confirms ready for conversion
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.
- 7d ago First seen · 98 lines · 17 tokens per session scan A 1eda02c407b8
debug-highlights is a skill published in the GitHub repository degiz/kobo2calibre (22 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 1,326 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.