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/sergei-aronsen/claude-code-toolkitWrote 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/commands/sergei-aronsen/claude-code-toolkit/setup-guide)<a href="https://agentmods.dev/commands/sergei-aronsen/claude-code-toolkit/setup-guide"><img src="https://agentmods.dev/badge/commands/sergei-aronsen/claude-code-toolkit/setup-guide/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/commands/sergei-aronsen/claude-code-toolkit/setup-guide"><img src="https://agentmods.dev/badge/commands/sergei-aronsen/claude-code-toolkit/setup-guide.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 | $0.00024 | $0.00602 |
| Opus 5.5 | $0.00010 | $0.00241 |
| Sonnet 5.5 | $0.00005 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
setup-guide scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
The post-install guide is what an end user sees right after running `bash <(curl -sSL .../scripts/install.sh)`. It only lists sections for things they actually installed — but their setup drifts after the first install ( How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/setup-guide
Purpose
Regenerate ~/.claude/setup-guide.html (or .claude/setup-guide.html if a project-local copy already exists) from the current state of installed toolkit components + MCP servers, then open it in the default browser.
The post-install guide is what an end user sees right after running bash <(curl -sSL .../scripts/install.sh). It only lists sections for things they actually installed — but their setup drifts after the first install (they enable a new MCP, install claude-memo later, etc.). This command rebuilds the guide so the page reflects the current machine.
Usage
/setup-guide
No arguments. Re-runs the generator and reopens the HTML in the browser. Honour TK_NO_OPEN=1 to skip auto-open in headless contexts.
What you should do
-
Locate the generator. In priority order:
~/.claude/scripts/lib/post-install-guide.sh(installed byupdate-toolkit)<repo>/scripts/lib/post-install-guide.sh(developer mode — running from inside a clone)
-
Run it. The script auto-detects:
- Components from filesystem probes (
~/.claude/CLAUDE.md,~/.claude/cc-safety-net.json,~/.claude/statusline-refresh.sh,rtkon PATH,~/.claude/council/brain.py,~/.claude/skills/memo-skill/.git, projectGEMINI.md/AGENTS.md). - MCPs from
~/.claude.json.mcpServerskeys.
- Components from filesystem probes (
-
Run with:
bash ~/.claude/scripts/lib/post-install-guide.sh. Default output is~/.claude/setup-guide.html. The script prints the path on success. -
Open the output:
- macOS:
open <path> - Linux:
xdg-open <path>
- macOS:
-
If the generator emits
templates dir not found, the user is missing thetemplates/post-install/payload. Tell them to run/update-toolkit(orbash <(curl -sSL .../scripts/install.sh)) so the templates land under~/.claude/templates/post-install/.
Output
A short confirmation: which components + which MCPs ended up in the guide, plus the absolute path of the generated HTML file. Do not dump the HTML.
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 · 47 lines · 24 tokens per session scan A 1506aaf1076c
setup-guide is a command published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 602 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.