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 skills/srombauts/sqlitecpp/skill-maintenancenpx skills add SRombauts/SQLiteCpp --skill skill-maintenancegit clone --depth 1 https://github.com/SRombauts/SQLiteCppWhat 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 | $0.00076 | $0.02108 |
| Opus 5 | $0.00038 | $0.01054 |
| Sonnet 5 | $0.00015 | $0.00422 |
| Haiku 4.5 | $0.00008 | $0.00211 |
Grade A, and why
skill-maintenance 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 2d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Maintenance
Editing conventions for files under .claude/skills/** (including SKILL.md and any
references/*.md). Does not apply to markdown elsewhere in the repo.
Apply on every edit. Do not retroactively rewrite skills that drift from these rules. Refactor
only when you are already editing the skill for another reason.
For the upstream specification, see Anthropic's Skill authoring best practices. The conventions below are repo-local extensions and reinforcements of that guide.
Markdown style
Wrap markdown at 100 characters. In rendered Markdown, single newlines fold into spaces, so wrapping does not affect the output, but it makes side-by-side diffs and review readable.
ASCII only. No emoji, no symbolic icons (warning signs, check marks, decorative arrows,
prohibition signs, etc.), no emoticons. Plain ASCII keeps git diff and GitHub's diff/blame views
readable and copy-pasteable, and stays consistent with the repo's .editorconfig (UTF-8 encoding,
but ASCII content avoids review surprises). For emphasis use bold, headings, or a leading word
like NEVER.
No em dashes or en dashes. Em dashes (—) and en dashes (–) are non-ASCII, so the
ASCII-only rule above already bans them. This line restates it because they slip in through
copy-paste and autocorrect. Do not use -- or - as a substitute; restructure instead:
a period (new sentence), a comma (a tight aside), a colon (an explanation), or parentheses (a true
aside). This keeps skill markdown consistent with the humanizer skill, which bans em dashes in
all published prose.
Frontmatter
Only name and description fields. No version, allowed-tools, or other keys unless a tool
actively reads them.
Use the YAML folded block scalar (>-) for any description longer than one line. Wrap lines at
100 chars inside the scalar; YAML folds them into one logical string.
description: >-
SQLiteCpp coding standards and API rules.
Use when editing core sources, changing public headers, adding Doxygen comments,
or enforcing RAII and naming conventions.
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.
- 2d ago First seen · 183 lines · 76 tokens per session scan A 31b30378379a
skill-maintenance is a skill published in the GitHub repository SRombauts/SQLiteCpp (2,781 stars, last pushed 6d ago), licensed MIT. It adds 76 tokens to every session and 2,108 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…