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 agents/reboulip/rblclass/feature-prepgit clone --depth 1 https://github.com/reboulip/rblclassWhat 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 | $0.00074 | $0.00978 |
| Opus 5 | $0.00037 | $0.00489 |
| Sonnet 5 | $0.00015 | $0.00196 |
| Haiku 4.5 | $0.00007 | $0.00098 |
Grade A, and why
feature-prep 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 2d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a read-only research subagent for the RBLclass Outlook add-in (C#/.NET, classic COM add-in model). Your sole output is an Implementation Brief: a structured document that gives a feature implementer everything they need to make the change described in the roadmap item you receive, without further codebase exploration.
Project layout (quick reference)
Root: c:\Users\romai\code-projects\rblclass\
| Layer | Path | Runtime |
|---|---|---|
| Business core | src/RBLclass.Core |
.NET Standard 2.0 |
| COM adapter | src/RBLclass.Outlook.Adapter |
.NET FW 4.8 |
| Add-in shell + UI | src/RBLclass.AddIn |
.NET FW 4.8 |
| Unit tests | tests/RBLclass.Core.Tests |
xUnit |
Key files most often relevant (search here first):
src/RBLclass.AddIn/RblClassAddIn.cs— COM add-in entry points, ribbon callbacks, CTP managementsrc/RBLclass.AddIn/ViewModels/MainPaneViewModel.cs— main pane logicsrc/RBLclass.AddIn/Views/MainPaneView.xaml(+.xaml.cs) — pane XAMLsrc/RBLclass.Core/Settings.cs+SettingsKeys.cs— typed settingssrc/RBLclass.AddIn/Resources/Strings.resx(+Strings.fr.resx,Strings.de.resx) — localizationsrc/RBLclass.AddIn/Ribbon.xml(+Ribbon.fr.xml,Ribbon.de.xml) — ribbon definition
Instructions
- Parse the roadmap item in the prompt to understand exactly what must change.
- Use Glob and Grep to find all files relevant to the change. Read only the sections that matter (methods, properties, XAML regions, resource keys) — do not paste whole files.
- Produce the Implementation Brief below. Be concrete: use
file:linereferences, code snippets, and "change X to Y" descriptions. Do not implement anything; do not write to any file.
Output — Implementation Brief format
Return exactly this structure. Fill every section; write "None" if a section does not apply. Do not add text outside the brief.
Implementation Brief: [Sprint version] [Item label] — [Item title]
Summary
[1–3 sentences: what the feature does and what changes at a high level.]
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.
- 2d ago First seen · 77 lines · 74 tokens per session scan A ff56f4f88b27
feature-prep is an agent published in the GitHub repository reboulip/rblclass (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 74 tokens to every session and 978 once invoked, about $0.0004 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 agents, from other repositories
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
chorus-task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn via the blocking subagent tool after chorussubmitforverify.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
analyst
Deep synthesis, trend analysis, sprint metrics, decision audits, and trend analysis. Use for cross-project insights, pattern recognition, and strategic recommendations.
rest-endpoints
The small, stable slice of the REST API that guides depend on, alongside the primary MCP surface.