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-fix)<a href="https://agentmods.dev/commands/wednesday-solutions/ai-agent-skills/brownfield-fix"><img src="https://agentmods.dev/badge/commands/wednesday-solutions/ai-agent-skills/brownfield-fix/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-fix"><img src="https://agentmods.dev/badge/commands/wednesday-solutions/ai-agent-skills/brownfield-fix.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 | $0.00944 |
| Opus 5 | $0.00000 | $0.00472 |
| Sonnet 5 | $0.00000 | $0.00189 |
| Haiku 4.5 | $0.00000 | $0.00094 |
Grade A, and why
brownfield-fix 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/brownfield-fix — Pre-Edit Risk Check
Purpose
Run a risk assessment before editing any file in a brownfield codebase. Provides a risk card showing impact scope, danger zones, and safe-to-edit verdict.
Trigger
- "Check the risk before I edit this"
- "What breaks if I change this file?"
- "Is this file safe to modify?"
Type: /brownfield-fix <file-path> (or leave empty to check currently open file)
Steps
1. Resolve the target file path
If $ARGUMENTS is empty, assume the currently open file in the editor.
If $ARGUMENTS is a relative path, resolve it relative to the project root.
2. Query the file summary from DB
const queries = require('./.wednesday/queries-loader.js'); // Loader helper
const fileSummary = queries.getFileSummary('.wednesday/graph.db', targetFile);
if (!fileSummary) {
console.log('File not found in graph. Run /brownfield-map first.');
return;
}
This single query returns:
- Risk score & band
- Git history (commits, bugs, age)
- Import counts (fan-in/fan-out)
- Blast radius (transitive dependents)
- Entry point info
- Circular dep membership
- Coverage gaps
3. Check for daemons and adapters
Daemons and adapters are included in the file summary from the DB:
- Daemon patterns (setInterval, cron, process.on) → recorded as
gap_type - Adapter references (database, HTTP, payment) → recorded in analysis
6. Build the risk card
Format:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
FILE: <relative-path>
RISK SCORE: <score>/100 [<band>]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
IMPACT SCOPE
Direct dependents: <N> files
Transitive affected: <N> files
CONTRIBUTING FACTORS
Bug fixes in history: <N>
Total commits: <N>
File age: <N> days
Import fanout: <N>
Unresolved gaps: <N>
DAEMONS & ADAPTERS
<list or "None">
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
VERDICT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[If SAFE or MODERATE]
✓ Safe to edit. Low blast radius. <one-line summary>
[If RISKY]
⚠ HIGH RISK. Affects <N> files. Review these before committing:
• <top impacted file 1>
• <top impacted file 2>
• <top impacted file 3>
[If CRITICAL]
🛑 CRITICAL. <reason>. Do NOT edit without:
1. Talking to the maintainer
2. Running full test suite
3. Code review from <most recent author>
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 · 129 lines · 0 tokens per session scan A af5b2a612d9f
brownfield-fix 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 944 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
api-aqa-flow-test-correction
Phase 7 Test Corrections of api-aqa-flow (USER APPROVAL REQUIRED).
ui-aqa-flow-test-correction
Phase 8 Test Correction of ui-aqa-flow.
ui-aqa-flow-test-report-analysis
Phase 7 Test Report Analysis of ui-aqa-flow.
api-aqa-flow-execution-and-report-analysis
Phase 6 Execution & Report Analysis of api-aqa-flow (USER INTERACTION REQUIRED).
debug-react
Inspect a live React runtime with React-Sentinel before editing source code.
reproduce-bug
Reproduce a React or browser bug with React-Sentinel before proposing a fix.