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.
git clone --depth 1 https://github.com/wednesday-solutions/ai-agent-skillsWrote 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/commands/wednesday-solutions/ai-agent-skills/brownfield-chat)<a href="https://agentmods.dev/commands/wednesday-solutions/ai-agent-skills/brownfield-chat"><img src="https://agentmods.dev/badge/commands/wednesday-solutions/ai-agent-skills/brownfield-chat/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/commands/wednesday-solutions/ai-agent-skills/brownfield-chat"><img src="https://agentmods.dev/badge/commands/wednesday-solutions/ai-agent-skills/brownfield-chat.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 | $0.00956 |
| Opus 5 | $0.00000 | $0.00478 |
| Sonnet 5 | $0.00000 | $0.00191 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
brownfield-chat 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 12d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/brownfield-chat — Natural Language Q&A
Purpose
Answer any structural, historical, or architectural question about the codebase without reading raw source files.
Trigger
- "What does X do?"
- "How does data flow from A to B?"
- "What breaks if I change this file?"
- "Which files handle authentication?"
- "What's the relationship between X and Y?"
Type: /brownfield-chat <question>
Steps
1. Understand the question
Parse the user's question to extract:
- Entity: which file, module, or pattern they're asking about (X, A, B, authentication, etc.)
- Relationship type: "what does", "how does", "what breaks", "which files", "relationship"
- Scope: single file, module, cross-module, or whole codebase
2. Search the codebase via DB
const queries = require('./.claude/query-helpers.js');
const results = queries.searchFiles(entityName);
This returns top matching files with full context:
- file_path, summary, purpose
- role, riskScore, importedByCount, importCount
- blastRadius (transitive dependents)
- entryPointConfidence
Return top 5 matching files.
3. For detailed file context, load full summary
const summary = queries.getFileSummary(dbPath, filePath);
Returns:
- filePath, lang, summary, purpose, primaryRole
- riskScore, band
- importedByCount, importCount (fan-in/fan-out)
- bugFixCommits, totalCommits
- isDeadFile, isCircularDep
- entryPointConfidence, dangerReason
- blastRadius (transitive impacts)
4. Answer the question
For "what does X do?"
Combine the file summary + purpose + role to answer in 2-3 sentences. Example: "auth.js is an Entry file (confidence 85%) that validates user credentials and manages JWT tokens. Imported by 8 files (api.js, middleware, routes). Risk score: 45 (Moderate)."
For "how does data flow from A to B?"
Use the import graph from file summaries to trace paths. If path exists: list it step-by-step. If no direct path: show closest path or note that they're unrelated.
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.
- 12d ago First seen · 115 lines · 0 tokens per session scan A 9e11a094b65d
brownfield-chat is a command published in the GitHub repository wednesday-solutions/ai-agent-skills (168 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 956 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.
Other commands, from other repositories
sdd-apply
Implement SDD tasks — writes code following specs and design.
sdd-explore
Explore and investigate an idea or feature — reads codebase and compares approaches.
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
gentle-sdd-ff
Fast-forward all SDD planning phases — proposal through tasks.
ink-art
Hand-drawn ink-on-white doodle animation — a character that draws itself then walks/dances/waves, or a deadpan contraption explainer. Vector, deterministic, rendered via HyperFrames to MP4.
modernization-flow
Workflow for converting, modernizing, upgrading, or re-architecting code (e.g. C++→Java, monolith→microservices), etc.