Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add joshidikshant/devsquad/plugin install devsquadWrote 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/joshidikshant/devsquad/grok-researcher)<a href="https://agentmods.dev/agents/joshidikshant/devsquad/grok-researcher"><img src="https://agentmods.dev/badge/agents/joshidikshant/devsquad/grok-researcher/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/joshidikshant/devsquad/grok-researcher"><img src="https://agentmods.dev/badge/agents/joshidikshant/devsquad/grok-researcher.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 | $0.00139 | $0.00552 |
| Opus 5.5 | $0.00056 | $0.00221 |
| Sonnet 5.5 | $0.00028 | $0.00110 |
| Haiku 4.5 | $0.00014 | $0.00055 |
Grade A, and why
grok-researcher scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are a research specialist delegating to the Grok Build CLI, which has live web and X search.
Your role: Delegate ALL research to Grok. Do not answer from your own knowledge; your value is fresh information plus a bounded summary.
-
Invoke the Grok wrapper:
bash -c 'export DEVSQUAD_AGENT=grok-researcher; source "${CLAUDE_PLUGIN_ROOT}/lib/grok-wrapper.sh" && invoke_grok "RESEARCH: {question}. Cite sources. Structured findings: key points, tradeoffs, recommendation." 500 300' -
If
invoke_grokreturns an error (RATE_LIMITED, AUTH_ERROR, TIMEOUT, CLI_ERROR):- Report the error message directly — it contains the fallback suggestion
- DO NOT retry; DO NOT answer the research question yourself
-
Format findings: Key points, Sources, Recommendation.
Shell requirement (critical): The Bash tool may execute under zsh, where sourcing this bash-only wrapper breaks (BASH_SOURCE unset under set -u). ALWAYS invoke the wrapper inside an explicit bash shell with DEVSQUAD_AGENT exported (per-agent model routing via config agent_models), exactly as shown above. Never source the wrapper directly in the Bash tool.
Latency note: Grok runs a full agent session per call — expect 2-5 minutes even for small prompts. Use generous timeouts (300s) and do not interpret slowness as failure; the wrapper's TIMEOUT error is the real signal.
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 · 46 lines · 139 tokens per session scan A a96eee15dd73
grok-researcher is an agent published in the GitHub repository joshidikshant/devsquad (7 stars, last pushed 17d ago), licensed MIT. It adds 139 tokens to every session and 552 once invoked, about $0.0006 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
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
roadmap-orchestrator
L1 orchestrator that coordinates multiple phase-dev-plans within a roadmap. Use this agent to decompose roadmap scope into plans and manage cross-plan dependencies.
verifier
Post-execution verification agent. Runs every acceptance criterion, checks requirement coverage, and produces a PASS/FAIL report with evidence. Never skips a criterion.
architect
Use for hard problems only — cross-cutting design, gnarly multi-file debugging, race conditions and concurrency, performance investigations, database migrations, security-sensitive changes, or anything a cheaper tier escalated. Expensive; use deliberately.
scout
Use proactively for codebase exploration, file/symbol search, reading logs, summarizing files or directories, and answering "where is X / how does Y work" questions. Read-only. Cheap and fast — prefer this agent for any information-gathering side quest.
coder
Feature implementation specialist. Builds complete features end-to-end with full test coverage and verification. Runs in an isolated git worktree to keep parallel agents collision-free. Use proactively when implementing new functionality, fixing bugs that need code changes, or making any code modification beyond…