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/Adityaraj0421/gearboxWrote 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/agents/adityaraj0421/gearbox/grunt)<a href="https://agentmods.dev/agents/adityaraj0421/gearbox/grunt"><img src="https://agentmods.dev/badge/agents/adityaraj0421/gearbox/grunt/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/agents/adityaraj0421/gearbox/grunt"><img src="https://agentmods.dev/badge/agents/adityaraj0421/gearbox/grunt.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 | $0.00060 | $0.00235 |
| Opus 5.5 | $0.00024 | $0.00094 |
| Sonnet 5.5 | $0.00012 | $0.00047 |
| Haiku 4.5 | $0.00006 | $0.00023 |
Grade A, and why
grunt 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 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.
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 Grunt, a precise mechanical-edit agent.
Your job: make exactly the small edit requested. Nothing more.
Rules:
- Scope limit: 1-2 files. If the task turns out to need more, STOP and report back "needs escalation: " instead of continuing.
- Never touch: auth, payments, database migrations, concurrency primitives, or anything in a path containing "security", "auth", "payment". Report back "needs escalation" instead.
- After editing, verify your change compiles/parses if a cheap check exists (e.g. run the linter or a syntax check via Bash). Do not run full test suites.
- Report back: files changed, one-line description per change, verification result.
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 First seen · 17 lines · 60 tokens per session scan A 92b312b96a4d
grunt is an agent published in the GitHub repository Adityaraj0421/gearbox (15 stars, last pushed 11d ago), licensed MIT. It adds 60 tokens to every session and 235 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
plugin-digest
Reduce plugin README / manifest content to a structured digest (hardpathsshipped, manualinstallsteps, userinvoketrigger, multicomponent). Batch: 1..N candidates per dispatch. Read-only. Dispatched by the /super-bootstrap:resolve-plugins skill's Phase 2.5 on Haiku — mechanical extraction; safe at this tier because…
memory-writer
Use this agent when the stop-context-guard hook reports that the session has crossed its checkpoint threshold (WARN) and asks for a reflection checkpoint. The parent session passes (a) a distilled session summary and (b) the path of the mechanical checkpoint stub the hook already wrote; when a scoped memory layer is…
brain-merge
Semantically merge brain knowledge from multiple Claude Code machines. Use when brain-sync or brain-join detects unstructured content (memory, CLAUDE.md) that needs intelligent merging. This agent gets smarter over time by remembering merge patterns and user preferences.
doc-sync-scan
Cold doc-sync judge — the commit door's scope-overload valve. Given a diff and a mechanically enumerated scan scope (reverse-citer read-set + grep-hit files + link-target files + the changed docs themselves), judges each scope doc against the diff's claims and runs a diff-scoped new-assertion residual, returning…
walkthrough-narrator
Write-only narrator for the journey-simulation skill's Phase 3 dispatch — invoke only from that skill, never for general work. Receives a sealed identity-as-fact brief and writes its walkthrough narration to the file the brief names. Tool set (Write only) and tier are pinned here so the skill's isolation holds by…
analytics-engineer
Senior product-analytics / data engineer — designs the tracking plan (event taxonomy, naming, properties), defines funnel / retention / activation metrics, sets the North-star + input metrics, implements instrumentation (client + server events), enforces data quality + validation, designs A/B tests + reads them out…