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 commands/design-and-deliver/claude-code-autoconfig/autoconfiggit clone --depth 1 https://github.com/design-and-deliver/claude-code-autoconfigWrote 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/design-and-deliver/claude-code-autoconfig/autoconfig)<a href="https://agentmods.dev/commands/design-and-deliver/claude-code-autoconfig/autoconfig"><img src="https://agentmods.dev/badge/commands/design-and-deliver/claude-code-autoconfig/autoconfig.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 5.1 | $0.00000 | $0.04006 |
| Opus 5 | $0.00000 | $0.02003 |
| Sonnet 5 | $0.00000 | $0.00801 |
| Haiku 4.5 | $0.00000 | $0.00401 |
Grade B, and why
autoconfig 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 today.
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.
Offer Claude Code's auto permission mode. This is deliberately a **user-level** opt-in: Claude Code ignores `permissions.defaultMode: "auto"` in project `.claude/settings.json` (a repository cannot grant itself auto mode How it starts
The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autoconfig
Configure Claude Code scaffolding for this project — settings, permissions, hooks, commands, and docs.
CLAUDE.md is intentionally kept minimal. Claude can read your config files directly — pre-populating project descriptions wastes tokens and dilutes important rules. Instead, CLAUDE.md grows organically through Discoveries as you work.
Setup Note: During autoconfig, prefer Glob/Read/Write tools over Bash commands. This ensures smooth setup without permission prompts. Only use Bash for the bootstrap step and opening the guide at the end.
Step 0a: Bootstrap files from latest package
MANDATORY: You MUST run this Bash command before doing anything else. Do not skip it. Do not assume it will fail. It is designed to work inside Claude Code sessions:
npx claude-code-autoconfig@latest --bootstrap
This downloads the latest package and copies slash commands, hooks, agents, docs, and settings into .claude/. The --bootstrap flag makes it safe to run inside Claude Code — it copies files and exits silently with code 0. If it fails (e.g., no network), continue anyway — the existing files will still work.
One failure is a hard stop. If the output says claude-code-autoconfig requires a newer Claude Code (● claude-code-autoconfig requires Claude Code vA.B.C or newer. followed by Your environment is running vX.Y.Z.), nothing was copied and nothing below can run correctly: the package's settings turn on Claude Code's Concise output style, which this version does not have. Show the user that block verbatim — the version required, the version found, and the claude update line — tell them to update Claude Code and then run /autoconfig again, and STOP. Do not continue to the later steps.
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.
- today Changed · +2 lines 77688195cb92
- 5d ago First seen · 291 lines · 0 tokens per session scan B a68f7457f2a4
autoconfig is a command published in the GitHub repository design-and-deliver/claude-code-autoconfig (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,006 tokens. 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 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.