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 skills add RBraga01/builder-product --skill feature-scopinggit clone --depth 1 https://github.com/RBraga01/builder-productWrote 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/rbraga01/builder-product/feature-scoping)<a href="https://agentmods.dev/skills/rbraga01/builder-product/feature-scoping"><img src="https://agentmods.dev/badge/skills/rbraga01/builder-product/feature-scoping/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/rbraga01/builder-product/feature-scoping"><img src="https://agentmods.dev/badge/skills/rbraga01/builder-product/feature-scoping.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 | $0.00049 | $0.01332 |
| Opus 5.5 | $0.00020 | $0.00533 |
| Sonnet 5.5 | $0.00010 | $0.00266 |
| Haiku 4.5 | $0.00005 | $0.00133 |
Grade A, and why
feature-scoping 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Scoping
The Law
A FEATURE ESTIMATED WITHOUT A WRITTEN SCOPE IS A COMMITMENT MADE AGAINST UNKNOWN WORK.
"Give me a rough number" produces a number that becomes a deadline before the scope is understood.
Written scope → time estimate against that scope → explicit commit IS a feature decision.
When to Use
Trigger before:
- Any request for an engineering estimate
- Any sprint planning that includes new functionality
- Any stakeholder conversation that will produce a commitment
- Any handoff from product to engineering
When NOT to Use
- Time-boxed spikes where the output is knowledge, not a feature (the scope is "spend N days and report back")
- Hotfixes with unambiguous scope (the scope is "fix the specific bug described in the issue")
The Scope Document
A scope document answers four questions before any estimate is given.
1 — What is being built?
User-visible behaviour only. Not implementation details.
The user can:
- [Action 1] — e.g., "filter search results by date range"
- [Action 2] — e.g., "export the filtered results as CSV"
The system will:
- [Behaviour 1] — e.g., "persist filter state across sessions"
2 — What is NOT being built in this scope?
Name the exclusions. Every implicit exclusion is a future dispute.
NOT included in this scope:
- [Exclusion 1] — e.g., "bulk export (> 1000 rows)"
- [Exclusion 2] — e.g., "real-time filter updates without page reload"
3 — What are the acceptance criteria?
Specific, testable conditions that define "done":
Given [state], when [action], then [observable result].
Acceptance criteria are the contract between product and engineering. Vague criteria ("works correctly") are not acceptance criteria.
4 — What are the dependencies and risks?
Dependencies:
- [Service/team/data that must be ready before this can ship]
Risks:
- [Known unknowns that could expand the estimate]
The Estimate Protocol
An estimate is only valid if it names the scope document it was made against.
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 · 158 lines · 49 tokens per session scan A f0b3813135cb
feature-scoping is a skill published in the GitHub repository RBraga01/builder-product (2 stars, last pushed 21d ago), licensed MIT. It adds 49 tokens to every session and 1,332 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 2026-08-31.
feature-scoping compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| feature-scopingRBraga01/builder-product | Skill | 2 | 21d ago | MIT | A | 49 | Claude Code |
| ai-engineering-toolkitsickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 47 | Claude Code |
| promptfoo-provider-setuppromptfoo/promptfoo | Skill | 27k | yesterday | MIT | A | 66 | Claude Code, Codex |
| prompt-masternidhinjs/prompt-master | Skill | 16k | 15d ago | MIT | B | 78 | Claude Code, Codex |
| flux2-lora-trainingAnastasiyaW/codex-claude-code-config | Skill | 214 | yesterday | MIT | A | 73 | Claude Code |
| refineSnowflake-Labs/cocoplus | Skill | 727 | 2d ago | MIT | A | 37 | Claude Code |
| pixel-art-studioAnastasiyaW/codex-claude-code-config | Skill | 214 | yesterday | MIT | A | 349 | Claude Code |