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/sqlitecpp-workflownpx skills add SRombauts/SQLiteCpp --skill sqlitecpp-workflowgit 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 | $0.00031 | $0.01200 |
| Opus 5 | $0.00015 | $0.00600 |
| Sonnet 5 | $0.00006 | $0.00240 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
sqlitecpp-workflow 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 yesterday.
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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SQLiteCpp Workflow
Required workflow
For an implementation request, complete the local Git workflow before handing the work back:
- Load
sqlitecpp-git-branching, inspectgit status, and create the task branch before editing. - Implement the change and its tests, public API documentation, and any required build-file updates.
- Build and run the relevant tests.
- Commit the completed work according to the atomic and independent commit rules below.
- Report the branch name, commit hashes, and validation results.
If work was accidentally started on master, create the correctly named branch immediately while
preserving the working tree, then continue the workflow there. Do not leave completed implementation
changes uncommitted unless the user explicitly asks for an uncommitted patch.
Change checklist
- Public API has Doxygen (
@brief,@param,@return,@throw). - Tests added under
tests/. - Build files updated (
CMakeLists.txt,meson.build). -
CHANGELOG.mdupdated for user-facing changes (in a separate commit after opening the PR).
CHANGELOG conventions
Update CHANGELOG.md in the same PR that makes the change, but in a separate commit created after
the PR is opened so the PR number is known. Normally add one line per PR under the current unreleased
version heading (Version X.Y.Z - <year> ???). Create that heading if it does not exist yet.
- Append a new bullet at the end of the current unreleased section by default. Do not reorder existing entries or insert the new entry by category unless there is a clear reason to group related changes.
- Related PRs may be kept together or combined when that makes the history clearer. For example, keep consecutive updates to the bundled SQLite library together instead of separating them by append order.
- Normally use one bullet per PR:
- <description> (#NNN). Keep all PR numbers at the end when related PRs share an entry:- <description> (#NNN) (#MMM). - Write in the imperative mood, present tense: "Add", "Fix", "Update", "Remove". Not "Added", "Fixes", or "Adding".
- Keep each entry to a single line that names the user-facing effect, not the internal mechanics.
- A change merged straight to master without a PR still gets a bullet; omit the
(#NNN)and note it was committed directly to master. - ASCII only, no em dashes. Run the entry through the
humanizerskill before committing so the prose stays plain and free of AI tells.
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.
- yesterday First seen · 92 lines · 31 tokens per session scan A 40f246d39243
sqlitecpp-workflow is a skill published in the GitHub repository SRombauts/SQLiteCpp (2,781 stars, last pushed 6d ago), licensed MIT. It adds 31 tokens to every session and 1,200 once invoked, about $0.0002 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…