toolkit

A command that lists the skills, agents, and commands available in the current project and recommends which may fit the current task. It first checks the repository and recent changes.

In plain words
What is it for?
Use it when joining an unfamiliar repository, deciding how to approach a task, checking installed capabilities, or seeing which tools match the current project.
Why use it?
It helps new users discover what the coding agent can use instead of guessing command names or relying on an outdated list.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/benkapner/claude-code-basecamp/toolkit
Clone the repo
git clone --depth 1 https://github.com/Benkapner/claude-code-basecamp

Made for: Claude Code.

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,113 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.01113
Opus 5 $0.00015 $0.00557
Sonnet 5 $0.00006 $0.00223
Haiku 4.5 $0.00003 $0.00111

Measured 2d ago against content hash 48d86be8b9d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

toolkit 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 2d 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.

.claude/commands/toolkit.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Toolkit Command

Help the user understand what tools are available and which ones to use right now.

Instructions

Step 1: Analyze Current Context

Quickly assess where the user is and what they might be working on:

# What repo are we in?
basename $(git rev-parse --show-toplevel 2>/dev/null) 2>/dev/null || echo "Not in a git repo"

# What changed recently?
git diff --name-only HEAD 2>/dev/null | head -10
git status --short 2>/dev/null | head -10

# What kind of project is this?
ls *.py pyproject.toml requirements*.txt config.yaml .env.example .mcp.json 2>/dev/null

Step 2: Discover Available Capabilities

Dynamically scan the workspace to find what's actually installed — never use a hardcoded list.

Find skills:

# List all skills and their descriptions
for skill_dir in skills/*/; do
  skill_file="$skill_dir/SKILL.md"
  if [ -f "$skill_file" ]; then
    name=$(basename "$skill_dir")
    desc=$(grep -A1 "^description:" "$skill_file" | tail -1 | sed 's/^[[:space:]]*//' | cut -c1-70)
    printf "  %-25s %s\n" "$name" "$desc"
  fi
done

Find commands:

# List all commands and their descriptions
for cmd_dir in commands/*/; do
  cmd_file="$cmd_dir/command.md"
  if [ -f "$cmd_file" ]; then
    name=$(basename "$cmd_dir")
    desc=$(grep "^description:" "$cmd_file" | head -1 | sed 's/description:[[:space:]]*"//;s/"$//' | cut -c1-60)
    printf "  /%-24s %s\n" "$name" "$desc"
  fi
done

Step 3: Present Capabilities

Present a clear overview organized by how they're used, populated from the scan results above:

WORKSPACE TOOLKIT
=================

SKILLS (activate automatically — you don't need to do anything):
────────────────────────────────────────────────────────────────
  [name]                  [description from SKILL.md]
  ...

COMMANDS (type these to trigger):
─────────────────────────────────
  /[name]              [description from command.md]
  ...

AGENTS (I spawn these automatically for parallel/specialized work):
──────────────────────────────────────────────────────────────────
  Explore            Fast codebase search across many files
  Plan               Design implementation strategies
  general-purpose    Complex multi-step research tasks

Read the full file on GitHub · 129 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. 2d ago First seen · 129 lines · 31 tokens per session scan A 48d86be8b9d9

Subscribe to this mod's changes

toolkit is a command published in the GitHub repository Benkapner/claude-code-basecamp (16 stars, last pushed 13d ago), licensed MIT. It adds 31 tokens to every session and 1,113 once invoked, about $0.0002 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.