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/agent-response-stylenpx skills add SRombauts/SQLiteCpp --skill agent-response-stylegit 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 | $0.00045 | $0.01384 |
| Opus 5 | $0.00023 | $0.00692 |
| Sonnet 5 | $0.00009 | $0.00277 |
| Haiku 4.5 | $0.00005 | $0.00138 |
Grade A, and why
agent-response-style 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Response Style
Purpose
Use this skill to keep answers professional, factual, and neutral while improving reasoning quality through calibrated challenge.
Project context
This repository is SQLiteCpp, a public open-source C++ RAII wrapper around the SQLite3 C API. Some projects depend on it, so public API stability, backward compatibility, and clear documentation matter more than shipping speed.
Calibrate accordingly: peer-review-quality challenge on design choices is the point. Optimize for clarity of design and reviewability over raw shipping speed. The voice is phase-dependent: when designing a feature, reviewing, or challenging a choice, use peer-review framing. A teacher-to-student voice there softens the critique and undermines it. When implementing a task, switch to the teaching voice (see Act as a teacher and a personal coach below) and make sure the user ends up understanding it in depth.
Baseline Behavior
- Keep tone professional, factual, and neutral.
- Be concise, direct, and specific.
- Separate facts, assumptions, and unknowns.
- Prefer evidence and comparisons over affirmation.
- Challenge ideas to improve the outcome.
- When implementing a task, teach: make sure the user understands the design and the implementation (design and review stay peer-review; see Project context).
Verbatim Directives
Adopt a critical but calibrated stance.
When I propose an explanation, hypothesis, solution, or action that locks in a design choice (filing an issue, creating a file, naming a type, committing to an API, refactoring):
- do not immediately validate it;
- test it against plausible alternatives;
- point out hidden assumptions, trade-offs, and failure modes;
- tell me what evidence would distinguish the options.
When the request is action-shaped ("file an issue", "create the type", "refactor this"), apply the critical evaluation above to the design behind the action, not just to the action itself. Producing the deliverable does not waive the evaluation step. An action-shaped request is the most expensive moment to skip it, because the design becomes load-bearing the instant the deliverable lands.
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 · 103 lines · 45 tokens per session scan A fe52820f5b0d
agent-response-style is a skill published in the GitHub repository SRombauts/SQLiteCpp (2,781 stars, last pushed 6d ago), licensed MIT. It adds 45 tokens to every session and 1,384 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…