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-update-sqlitenpx skills add SRombauts/SQLiteCpp --skill sqlitecpp-update-sqlitegit 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 | $0.00061 | $0.00686 |
| Opus 5 | $0.00030 | $0.00343 |
| Sonnet 5 | $0.00012 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
sqlitecpp-update-sqlite 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Updating the bundled SQLite3
SQLiteCpp ships a copy of the SQLite3 amalgamation under sqlite3/ so the CMake build works with
no system dependency. The Meson build instead pulls SQLite from wrapdb via a wrap file. An upgrade
touches both.
Do this on a dedicated branch named update-sqlite-X.Y.Z (for example update-sqlite-3.52.2),
matching the SQLite version you are moving to.
1. Download the amalgamation
Get sqlite-amalgamation-NNNNNNN.zip from the SQLite download page.
NNNNNNN encodes the version with two digits per component: 3.51.3 is 3510300.
2. Replace the vendored files
Extract and overwrite, verbatim, with the files from the zip:
sqlite3/sqlite3.csqlite3/sqlite3.h
Do not hand-edit them. Build-time feature flags (SQLITE_OMIT_LOAD_EXTENSION,
SQLITE_ENABLE_COLUMN_METADATA, and the rest in [[sqlitecpp-sqlite-flags]]) are passed as compile
definitions, never by patching the amalgamation.
3. Update sqlite3/README.md
- The amalgamation line: filename, version, and release date, e.g.
"sqlite3.c" and "sqlite3.h" files from sqlite-amalgamation-3510300.zip (SQLite 3.51.3 2026-03-13) - The copyright year, if the year has rolled over.
4. Update the copyright year
Bump the year in sqlite3/CMakeLists.txt if it changed (it tracks the same 2012-<year> range).
5. Update the Meson wrap (separate concern)
subprojects/sqlite3.wrap points at a wrapdb release and can lag behind the CMake amalgamation
version. Bump it to the matching sqlite3_X.Y.Z-N package (the directory, source_url,
source_filename, source_hash, patch_*, and wrapdb_version fields). This is often a separate
PR from the amalgamation drop.
6. Build, test, and record
- Build and run the tests on both CMake and Meson (see [[sqlitecpp-build-cmake]] and [[sqlitecpp-build-meson]]).
- Update
CHANGELOG.mdfollowing [[sqlitecpp-workflow]] conventions: Add one line (or update the existing one) under the current unreleased version heading:- Update SQLite from A.B.C to X.Y.Z (YYYY-MM-DD) (#NNN).
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 · 54 lines · 61 tokens per session scan A 4fe2c6e88e56
sqlitecpp-update-sqlite is a skill published in the GitHub repository SRombauts/SQLiteCpp (2,781 stars, last pushed 6d ago), licensed MIT. It adds 61 tokens to every session and 686 once invoked, about $0.0003 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…