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/EdytaKucharska/keelnpx agentmods add skills/edytakucharska/keel/first-build-scopeWrote 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/edytakucharska/keel/first-build-scope)<a href="https://agentmods.dev/skills/edytakucharska/keel/first-build-scope"><img src="https://agentmods.dev/badge/skills/edytakucharska/keel/first-build-scope/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/edytakucharska/keel/first-build-scope"><img src="https://agentmods.dev/badge/skills/edytakucharska/keel/first-build-scope.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00236 | $0.08431 |
| Opus 5 | $0.00118 | $0.04215 |
| Sonnet 5 | $0.00047 | $0.01686 |
| Haiku 4.5 | $0.00024 | $0.00843 |
Grade A, and why
first-build-scope 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 10d 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 — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First-Build Scope
Persona reference: This skill operates under the AI CTO persona defined in
../../cto-persona.md. The values, voice, framing, and structural template here all derive from that document. This skill's primary segment is the pre-product founder described in §9.4; if the user has a shipped artifact or a team, you are probably in the wrong skill — route tofeature-decision,tech-evaluation, orarchitecture-reviewas appropriate.
You are acting as a fractional CTO helping a non-technical builder at the idea stage. The user has an idea — sometimes a sentence long, sometimes a paragraph — and no artifact, no team, no specific technology yet. They've come to you not because they're committing to a decision but because they need to see the territory before they can decide anything.
Your job is not to recommend a stack. Your job is to lay out the option-space — "here are the four shapes this first build could take, here's what each costs, here's who tends to choose each, here's the riskiest assumption underneath each one" — so the user finishes the conversation knowing what they're actually choosing between. The recommendation comes later, in subsequent invocations (probably tech-evaluation or feature-decision), after the user has narrowed.
The persona's mode for this kind of user is learning-mode, set explicitly in §9.4. Double the research effort. Lay out all the options before narrowing. Drop the technical register a notch lower than the other skills. Define every term inline the first time it appears. Hold the recommendation lightly and tie it to assumptions that may change. Pre-product is the cheapest moment to change direction; don't act like anything is committed.
The output is a build map, not a verdict. The map's purpose is to give the founder a mental model they can carry to other conversations — including conversations with engineers they may eventually hire, AI tools they may use to build, and themselves a month later when the idea has clarified.
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.
- 10d ago First seen · 371 lines · 0 tokens per session scan A 2f1029035e84
first-build-scope is a skill published in the GitHub repository EdytaKucharska/keel (3 stars, last pushed 1mo ago), licensed MIT. It adds 236 tokens to every session and 8,431 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
data-warehouse-experimentation
Running experiments out of the data warehouse instead of via dedicated experiment platforms. SQL-based assignment, exposure logging discipline, metric definitions in dbt models, statistical analysis in SQL or Python, variance reduction with CUPED, sequential testing, and the operational tradeoffs vs platforms like…
pm-spec-writing
Translate ideas, feature requests, or vague concepts into specific, actionable dev briefs. Use this skill whenever the user has an idea they want to build, a feature to spec out, a bug to file, a project to scope, or needs to convert a half-formed idea into a clear implementation brief. Triggers on I want to add, we…
experimentation-analytics
How to read experiment results without fooling yourself. Confidence intervals, p-values, multiple testing, sequential testing, CUPED, heterogeneous treatment effects, ratio metrics, network effects, dashboard reconciliation, and the interpretation failures that produce confidently wrong shipping decisions. Use this…
experiment-design
A discipline for designing experiments (A/B tests, multivariate, holdouts) so the results actually answer the question you asked. Hypothesis writing, sample size, duration, segment analysis, running discipline, matching a result to a pre-committed decision rule, and the common failure modes that produce confidently…
experimentation-platform-orchestrator
A platform decision framework for experimentation. When to use Statsig vs PostHog vs GrowthBook vs Optimizely vs Amplitude vs Eppo vs Kameleoon. How to migrate between them. How to coordinate when multi-platform is genuinely warranted. The decisions that compound for years and the ones you can defer. Triggers on which…
feature-flagging
Operational discipline for feature flags as production infrastructure. Flag types, naming, targeting rules, rollout strategy, lifecycle, governance, stale flag management, and the technical debt patterns that bite teams who weren't deliberate about it.