researcher

researcher is a skill for Claude Code from keli-wen/agy-staff. It costs 75 tokens per session (915 once invoked), scanned A, original, MIT.

A skill that sends a research request to Google's Antigravity CLI, a command-line tool that delegates work to Google's Gemini model. It starts a background job and provides a command for collecting the report later.

In plain words
What is it for?
Use it for deep research or surveys of a topic or codebase, then wait for the background job and collect its report.
Why use it?
It lets another agent perform a longer independent investigation while the main session continues working.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Run this command **unsandboxed** — agy needs a localhost port and its OAuth token file, which harness sandboxes hide. In Codex, request escalated permissions fo.

Part of the agy plugin — 14 skills shipped together

Good fit Use it for deep research or surveys of a topic or codebase, then wait for the background job and collect its report.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/keli-wen/agy-staff
agentmods
npx agentmods add skills/keli-wen/agy-staff/researcher

Made for: Claude Code.

Or install agy, the plugin that ships this one along with the rest of its 14 skills.

Wrote 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.

agentmods badge for researcher

README.md
[![agentmods](https://agentmods.dev/badge/skills/keli-wen/agy-staff/researcher/github.svg)](https://agentmods.dev/skills/keli-wen/agy-staff/researcher)
Your own site
<a href="https://agentmods.dev/skills/keli-wen/agy-staff/researcher"><img src="https://agentmods.dev/badge/skills/keli-wen/agy-staff/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.

agentmods 80×15 button for researcher

Your own site · 80×15
<a href="https://agentmods.dev/skills/keli-wen/agy-staff/researcher"><img src="https://agentmods.dev/badge/skills/keli-wen/agy-staff/researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 915 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 14
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00075 $0.00915
Opus 5 $0.00037 $0.00458
Sonnet 5 $0.00015 $0.00183
Haiku 4.5 $0.00007 $0.00092

Measured yesterday against content hash a4a27979dcb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

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 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.

skills/researcher/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agy researcher

Delegate a research task to the agy staffer via the shared companion script. You are a thin shell: build the command, run it, return agy's report verbatim.

Locating the companion

This skill file lives at <plugin-root>/skills/researcher/SKILL.md; resolve the companion path relative to this skill directory:

node "<skill-dir>/../../companion/agy-companion.mjs" research [flags] --prompt "what to research"

Pass the user's research topic verbatim via --prompt; use --prompt-file <path> or --stdin for a long brief.

[!IMPORTANT] Run this command unsandboxed — agy needs a localhost port and its OAuth token file, which harness sandboxes hide. In Codex, request escalated permissions for the command. Details: ../jobs/references/troubleshooting.md.

Collecting the result

The command returns a job id. Read ../jobs/SKILL.md for result collection and recovery: dispatch, wait for the final result, then validate as needed. Do not proactively observe progress, read logs or inspect intermediate artifacts while running. Observe only when the user explicitly asks for progress; diagnose a failure or a result requiring intervention under the jobs protocol.

Flags (all optional)

  • --continue — reuse the last research conversation (quota-friendly, served largely from cache); --conversation <id> targets a specific one.
  • --model <id> or --effort low|medium|high — default model is gemini-3.8-flash-high.
  • --restricted / --unrestricted — permission profile. research defaults to unrestricted, so it works out of the box with no setup. --restricted is the opt-in hardening path: agy runs without --dangerously-skip-permissions and may only use allowlisted tools, so it needs the setup flow's evidence-gathering allowlist to be useful — and some native agy tools ignore allow-rules headless, so restricted runs can still come back empty.
  • --prompt <text> / --prompt-file <path> / --stdin — the task, from exactly one of these three sources. Use file/stdin for long prompts.
  • --timeout <dur> — default 60m, maximum 120m hard execution limit.

Read the full file on GitHub · 46 lines

Changes

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.

  1. yesterday Changed a4a27979dcb2
  2. 2d ago Changed · -2 lines fe4e8a365c6a
  3. 6d ago Changed 529fa0fde100
  4. 11d ago First seen · 48 lines · 75 tokens per session scan A 5d7e6d9896d0

Subscribe to this mod's changes

researcher is a skill published in the GitHub repository keli-wen/agy-staff (124 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 915 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

mantis-reproduce

Generates and runs crash reproducers to verify security flaws. Use when viable findings exist and you need to write and execute a script or payload to verify the crash. Don't use for code auditing or patching.

google/mantis · 47 tokens

conductor-implement

Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.

gemini-cli-extensions/conductor · 34 tokens

mantis-meta-agent

Acts as the persistent supervisor, launching and monitoring the automated review campaign. Use when running a long-running, continuous security review campaign that needs autonomous coordination. Don't use for executing individual review stages directly.

google/mantis · 44 tokens

writing-python

How Python is written in this repo — free functions over classes, structured returns instead of mutated arguments, comprehensions, no module state, and the stdlib-only, annotation-free, Python 3.8 dialect the AST lints enforce. Covers modular structure and the import-layer rule, DRY without copying a helper into a…

AleksandarBisevac/claude-plugins · 161 tokens

cleanup

Clean up after a merged pull request — return to the base branch, remove the worktree, delete the branch, sweep other stale branches and worktrees, and report tracker state. Use after a merge or whenever asked what is left over.

mikestankavich/claude-ship-workflow · 0 tokens

cc-query-performance-safety

A safety workflow for code that performs repeated database queries, large ID-list queries, graph or recursive traversal, or nested service calls.

doccker/cc-use-exp · 66 tokens