Borrowing it
Nothing to install: this file belongs to reboulip/rblclass. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/reboulip/rblclass/main/.claude/skills/feature-impl/SKILL.mdgit clone --depth 1 https://github.com/reboulip/rblclassWrote 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/reboulip/rblclass/feature-impl)<a href="https://agentmods.dev/skills/reboulip/rblclass/feature-impl"><img src="https://agentmods.dev/badge/skills/reboulip/rblclass/feature-impl/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/reboulip/rblclass/feature-impl"><img src="https://agentmods.dev/badge/skills/reboulip/rblclass/feature-impl.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 | $0.00000 | $0.01984 |
| Opus 5.5 | $0.00000 | $0.00794 |
| Sonnet 5.5 | $0.00000 | $0.00397 |
| Haiku 4.5 | $0.00000 | $0.00198 |
Grade A, and why
feature-impl 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/feature-impl — implement one sprint item end-to-end
Prerequisites
An Implementation Brief (produced by the feature-prep subagent) must be
in the current conversation context. If one is not present, invoke it now:
Agent({
subagent_type: "feature-prep",
description: "Prepare implementation brief",
prompt: "Sprint: [version]\nItem: [label] — [title]\n\n[full roadmap item text]"
})
Then continue once the brief is returned.
Step 1 — State the item
Before touching any file, state clearly which item you are implementing (e.g. "Implementing v2.4.0.0 A1 — Clear the search field after classify"). This anchors the conversation.
Step 2 — Implement
Work through each file in the brief's "Files to modify" and "Files to create" sections. Read the current file content (or the relevant section) before editing. Apply exactly the changes described in "Required changes" — no opportunistic refactoring of surrounding code.
Follow CLAUDE.md coding rules throughout: no comments unless the WHY is non-obvious, no extra abstractions, no error handling for impossible cases.
Step 3 — Localization
For every key listed in the brief's "Localization" section:
- Add the key + English value to
src/RBLclass.AddIn/Resources/Strings.resx. - Add translated values to
Strings.fr.resxandStrings.de.resx.
ResourceParityTests fails the build if any key is missing or has mismatched
{n} placeholders — never skip this step.
Step 4 — xUnit tests
For every test case in the brief's "xUnit tests" section:
- Add it to the specified test class in
tests/RBLclass.Core.Tests/. - Run
dotnet test tests/RBLclass.Core.Tests/ --verbosity minimaland confirm all tests pass before proceeding.
Step 5 — Build check
msbuild is not on PATH on this machine — resolve it via vswhere first
(same lookup Reload-Addin.ps1 uses), then build to catch compilation
errors before reloading into Outlook:
$vswhere = "${env:ProgramFiles(x86)}\Microsoft Visual Studio\Installer\vswhere.exe"
$msbuild = & $vswhere -latest -prerelease -products * -requires Microsoft.Component.MSBuild -find "MSBuild\**\Bin\MSBuild.exe" | Select-Object -First 1
if (-not $msbuild -or -not (Test-Path $msbuild)) { throw "MSBuild not found via vswhere." }
& $msbuild "src\RBLclass.AddIn\RBLclass.AddIn.csproj" /p:Configuration=Debug "/p:Platform=Any CPU" /t:Build /v:minimal /nologo
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 · 173 lines · 0 tokens per session scan A 9f1561cc8773
feature-impl is a skill published in the GitHub repository reboulip/rblclass (12 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,984 tokens. 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.
feature-impl compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| feature-implreboulip/rblclass | Skill | 12 | yesterday | Apache-2.0 | A | 0 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |