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/efilkucf/mysql-mcp-plugin/testgit clone --depth 1 https://github.com/Efilkucf/mysql-mcp-pluginWhat 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 | $0.00014 | $0.00340 |
| Opus 5 | $0.00007 | $0.00170 |
| Sonnet 5 | $0.00003 | $0.00068 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade B, and why
test scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
|| find ~/.claude/plugins -name cli.js -path '*mysql*' -not -path '*/node_modules/*' 2>/dev/null | head -1 What it actually says
Test the connection named in $ARGUMENTS.
Resolve the CLI path:
ls "${CLAUDE_PLUGIN_ROOT}/dist/cli.js" 2>/dev/null \
|| find ~/.claude/plugins -name cli.js -path '*mysql*' -not -path '*/node_modules/*' 2>/dev/null | head -1
Then run:
node <resolved-path> test $ARGUMENTS
If no name was given, run list first and ask which connection to test.
The command connects (opening the SSH tunnel if the connection uses one), reports
the MySQL version and effective user, prints SHOW GRANTS, and compares the
declared capabilities against what the account can actually do.
When interpreting the result for the user:
- Declared but not granted — those operations will fail at the database even though the plugin permits them. The GRANT needs widening, or the capability should be revoked to match reality.
- Granted but not declared — MySQL would allow more than the plugin does. Not necessarily wrong, since the account may be shared with other consumers, but worth knowing: the plugin refuses those before they reach MySQL.
If the connection fails, read the error carefully — it distinguishes an unreachable host from an auth failure from a missing database, and for loopback addresses it flags a probably-dead tunnel.
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 · 40 lines · 14 tokens per session scan B 4bd5db339f7a
test is a command published in the GitHub repository Efilkucf/mysql-mcp-plugin (0 stars, last pushed 20d ago), licensed MIT. It adds 14 tokens to every session and 340 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.