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/iBrain-BVBA/gutt-claude-code-pluginWrote 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/ibrain-bvba/gutt-claude-code-plugin/health)<a href="https://agentmods.dev/commands/ibrain-bvba/gutt-claude-code-plugin/health"><img src="https://agentmods.dev/badge/commands/ibrain-bvba/gutt-claude-code-plugin/health/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/ibrain-bvba/gutt-claude-code-plugin/health"><img src="https://agentmods.dev/badge/commands/ibrain-bvba/gutt-claude-code-plugin/health.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 | $0.00025 | $0.00734 |
| Opus 5.5 | $0.00010 | $0.00294 |
| Sonnet 5.5 | $0.00005 | $0.00147 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade B, and why
health 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.claude/settings.json` instead and report one of: How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Health Dashboard
Run a quick diagnostic of the gutt-pro plugin and display a status report.
Steps
1. Check MCP Connectivity
Use the diagnoseGuttMcp() function from hooks/lib/mcp-config.cjs:
const { diagnoseGuttMcp } = require("./hooks/lib/mcp-config.cjs");
const diag = diagnoseGuttMcp();
Report:
- configured: whether gutt MCP server is found in settings
- url: the resolved HTTP URL (or "N/A — stdio transport")
- error: any configuration error message
2. List Registered Hooks
Read hooks/hooks.json from the plugin root. For each hook event present, list:
- Event name
- Number of registered hook commands
- Matcher patterns (if any)
3. Check the statusline
The plugin manifest carries no statusLine, and must not — Claude Code accepts one
only from the user's own settings, so a key here would be inert. Look in
~/.claude/settings.json instead and report one of:
- installed — a
statusLinewhose command points atstatusline.cjsunder the plugin's data directory. This is the healthy state. - installed, but stale — a
statusLinepointing atstatusline.cjssomewhere under a plugin cache path. That is a version-scoped directory an upgrade replaces, so it will break. Tell them/gutt-pro:statuslinerepoints it at a stable path. - someone else's — a
statusLinepointing anywhere else. Leave it alone and say so; the gutt HUD cannot be installed without removing theirs first. - not installed — no
statusLineat all. Mention/gutt-pro:statuslineif they want one; do not treat its absence as a fault.
If it is absent but the runtime config records that they installed it, say the key was dropped from settings — Claude Code does that when it rewrites the file — and that the next session restores it.
4. Count Components
List the agents/ directory in the plugin root and count .md files (excluding any
starting with _). List skills/ and count immediate subdirectories containing a
SKILL.md.
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.
- 1mo ago Changed · +3 lines · +1 tokens per session 7a3170f010f1
- 1mo ago First seen · 92 lines · 24 tokens per session scan B 3c42b999f5c3
health is a command published in the GitHub repository iBrain-BVBA/gutt-claude-code-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 734 once invoked, about $0.0001 per session on Opus 5.5. 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
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.