Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/giang6283623/minimal-vibe-coding-kitnpx agentmods add skills/giang6283623/minimal-vibe-coding-kit/autoresearch-codingWrote 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/giang6283623/minimal-vibe-coding-kit/autoresearch-coding)<a href="https://agentmods.dev/skills/giang6283623/minimal-vibe-coding-kit/autoresearch-coding"><img src="https://agentmods.dev/badge/skills/giang6283623/minimal-vibe-coding-kit/autoresearch-coding/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/giang6283623/minimal-vibe-coding-kit/autoresearch-coding"><img src="https://agentmods.dev/badge/skills/giang6283623/minimal-vibe-coding-kit/autoresearch-coding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00057 | $0.01747 |
| Opus 5.5 | $0.00023 | $0.00699 |
| Sonnet 5.5 | $0.00011 | $0.00349 |
| Haiku 4.5 | $0.00006 | $0.00175 |
Grade A, and why
autoresearch-coding 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 2mo 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autoresearch Coding Loop
Run a controlled experiment loop. Do not perform open-ended destructive work.
Contract
Extract or infer:
- Goal and observable success condition.
- Metric command as an argument vector, not an interpolated shell string.
- Metric extraction rule, direction (
lowerorhigher), minimum meaningful delta, and accepted exit codes. - Repeat count, aggregation, tolerance, and warmup policy. Default to one measured run only for deterministic checks; otherwise use at least three and report variance.
- Editable paths.
- Protected paths, including metric scripts, fixtures, expected outputs, and other oracle assets.
- Budget, default 3.
- Per-run timeout, default 10 minutes.
- Required environment, tool versions, seed, and network or service dependencies.
If the metric command or editable scope is missing, infer conservative defaults and show the contract before editing. If no safe metric exists, ask for one. Always print the resolved contract before the baseline run, label inferred fields, and fail closed when editable and protected paths overlap.
Treat a metric command as executable authority. Prefer a repository-owned, already documented validation command. Inspect unfamiliar scripts before running them. Do not use deploys, migrations, package lifecycle scripts, untrusted hooks, or commands with external side effects as a metric unless the user explicitly authorizes that exact effect. Pass commands to scripts/run_logged.py as argv after --; never concatenate user-controlled text into a shell command.
For this kit itself, use:
goal: improve Minimal Vibe Coding Kit quality
metric command: node .vibekit/scripts/validate-kit.mjs .
direction: higher
metric extraction: exit 0 = 1, validation failure = 0; warnings are a secondary measure
minimum delta: 1, except an equal score may keep a predeclared safety simplification with focused regression proof
measurement: deterministic, 1 run, tolerance 0, no warmup
editable paths: .vibekit/docs .vibekit/scripts .vibekit/skills .vibekit/commands .claude .cursor .agents .grok .kimi-code .codex .codex-plugin .github README.md AGENTS.md .vibekit/init/CLAUDE-template.md .vibekit/init/FIRST_TIME_INIT.md .vibekit/init/FIRST_PROMPT.md backbone.yml package.json install.sh install.ps1
protected paths: .git .env* node_modules vendor secrets lockfiles and the metric oracle unless a new contract is approved
budget: 3
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 119 lines · 57 tokens per session scan A 757c8b3a13c1
autoresearch-coding is a skill published in the GitHub repository giang6283623/minimal-vibe-coding-kit (26 stars, last pushed 18d ago), licensed MIT. It adds 57 tokens to every session and 1,747 once invoked, about $0.0002 per session on Opus 5.5. 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.