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 commands/vepo/issues/fix_sonar_issuesgit clone --depth 1 https://github.com/vepo/issuesWhat 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 | $0.00020 | $0.00440 |
| Opus 5 | $0.00010 | $0.00220 |
| Sonnet 5 | $0.00004 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
Fix Sonar Issues 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 yesterday.
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.
What it actually says
You are an expert Java developer working on Issues. Fix all issues surfaced by local static analysis — the same class of problems SonarCloud flags, without calling SonarCloud or using any token.
Align with static-analysis.mdc: local checks only.
Follow this loop — do not ask for confirmation before editing.
1. Discover issues (local)
mvn -B compile -Dmaven.compiler.showWarnings=true -Dmaven.compiler.showDeprecation=true
Scan IDE diagnostics: ReadLints on changed src/main/java and src/test/java.
Do not call SonarCloud API.
2. Prioritize
- Compile errors, failing
verify - Reliability smells: empty catches,
System.out,printStackTrace - Compiler + linter warnings: unused code, deprecations
- Maintainability: cognitive complexity, duplicated literals
3. Fix strategies
| Theme | Safe approach | Avoid |
|---|---|---|
| Unused imports / dead code | Remove after confirming zero references | Deleting public API |
| Exception handling | SLF4J + rethrow or IssuesException |
Empty catch |
| Test smells | Fix assertion or setup | @Disabled, weakened assertions |
| HTTP contract | Use *Request/*Response records |
VO/DTO suffix |
Never: weaken workflow validation; delete tests to green CI.
4. Verify each batch
mvn formatter:format
mvn -B verify
5. Log every change
Append to reports/sonar_fix_log-{sequential}-{dd-MM-yyyy-HH-mm-ss}.md.
6. Stop when
mvn verifypassesReadLintsclean on touched files
Print ✅ Local static analysis clean! and summarize.
Start the loop now.
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.
- yesterday First seen · 59 lines · 20 tokens per session scan A 2e8f1e29b632
Fix Sonar Issues is a command published in the GitHub repository vepo/issues (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 440 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
plan
Run /plan — see .claude/commands/plan.md for the authoritative spec.
wire-harness
Run /wire-harness — see .claude/commands/wire-harness.md for the authoritative spec.
build
Run /build — see .claude/commands/build.md for the authoritative spec.
ship
Run /ship — see .claude/commands/ship.md for the authoritative spec.
onboard
Run /onboard — see .claude/commands/onboard.md for the authoritative spec.
review
Run /review — see .claude/commands/review.md for the authoritative spec.