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 skills/kimgoetzke/coding-agent-configs/research-modenpx skills add kimgoetzke/coding-agent-configs --skill research-modegit clone --depth 1 https://github.com/kimgoetzke/coding-agent-configsWrote 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/skills/kimgoetzke/coding-agent-configs/research-mode)<a href="https://agentmods.dev/skills/kimgoetzke/coding-agent-configs/research-mode"><img src="https://agentmods.dev/badge/skills/kimgoetzke/coding-agent-configs/research-mode.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.02429 |
| Opus 5 | $0.00031 | $0.01215 |
| Sonnet 5 | $0.00012 | $0.00486 |
| Haiku 4.5 | $0.00006 | $0.00243 |
Grade B, and why
research-mode 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 5d 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 Code | `~/.claude/settings.json` | _(none — default)_ | How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Usage
/research-mode— Enable research mode, then prompt for a topic/research-mode <topic>— Enable research mode and start researching the topic/research-mode continue— List existing research docs and resume one/research-mode off— Disable research mode
Configuration
Hook configuration by tool
| Tool | Hook config location / equivalent | Script format argument |
|---|---|---|
| Claude Code | ~/.claude/settings.json |
(none — default) |
| Copilot | ~/.copilot/hooks.json |
copilot |
| Pi | Bundled active-mode extension in .pi/agent/extensions/active-mode/ |
(extension-driven) |
Claude Code and Copilot support the bundled PostToolUse and SessionStart hook scripts directly. Pi does not use the same standalone hook configuration files in this repository's starter config. Instead, this starter config now ships a Pi-native active-mode extension that reads .ai/.active-mode, clears stale flags on fresh session start, injects reminder context before LLM calls, and shows mode status in the UI. If that extension is not installed, fall back to manual document updates.
If you cannot determine which tool you are, ask the user.
Workflow
Step 1: Check hook configuration
If the argument is "off", skip this step and go directly to Step 2.
Otherwise:
- If running in Claude Code, run
bash {skill-dir}/scripts/check-hooks.shand parse the structured output. - If running in Copilot, run
bash {skill-dir}/scripts/check-hooks.sh copilotand parse the structured output. - If running in Pi, skip the standalone hook check. Explain that this repository's Pi starter config uses the bundled
active-modeextension instead of standalone hook files. If that extension is installed, research mode gets equivalent reminder/cleanup behaviour automatically. Otherwise research mode will rely on manual update discipline only. Then continue to Step 2.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 215 lines · 62 tokens per session scan B 9022b6e0a841
research-mode is a skill published in the GitHub repository kimgoetzke/coding-agent-configs (2 stars, last pushed 16d ago), licensed MIT. It adds 62 tokens to every session and 2,429 once invoked, about $0.0003 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 skills, from other repositories
codebase-memory
Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions…
using-pi-subagents
Operate pi-subagents jobs safely, including direct-work decisions, least-privilege tool selection, thinking-level selection, delegation, bidirectional messaging, parallel starts, timeout selection, waiting, cancellation, result handling, verification, and writer isolation.
configuring-pi-starship
Configure @narumitw/pi-starship and answer questions about its pi-starship.toml settings. Use when the user asks to create, edit, repair, migrate, or understand pi-starship.toml, or asks which pi-starship module, variable, option, style, palette, preset, or runtime behavior to use. Do not use for generic TOML, shell…
skill-creator
Create or update Agent Skills (SKILL.md plus optional scripts, references, or assets). Use when someone asks to design a new Agent Skill, refine an existing one, or structure skills for Pi discovery, packaging, or other Agent Skills-compatible clients.
pi-ralph-wiggum
Long-running iterative development loops with pacing control and verifiable progress. Use when tasks require multiple iterations, many discrete steps, or periodic reflection with clear checkpoints; avoid for simple one-shot tasks or quick fixes.
surf
Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.