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 skills add byerlikaya/claude-starter-kit --skill automode-policygit clone --depth 1 https://github.com/byerlikaya/claude-starter-kitWrote 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/byerlikaya/claude-starter-kit/automode-policy)<a href="https://agentmods.dev/skills/byerlikaya/claude-starter-kit/automode-policy"><img src="https://agentmods.dev/badge/skills/byerlikaya/claude-starter-kit/automode-policy/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/skills/byerlikaya/claude-starter-kit/automode-policy"><img src="https://agentmods.dev/badge/skills/byerlikaya/claude-starter-kit/automode-policy.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 | $0.00041 | $0.01549 |
| Opus 5 | $0.00020 | $0.00775 |
| Sonnet 5 | $0.00008 | $0.00310 |
| Haiku 4.5 | $0.00004 | $0.00155 |
Grade B, and why
automode-policy 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 11d 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.
The classifier reads `autoMode` from **user** settings (`~/.claude/settings.json`) or **managed** settings. How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-mode policy (automode-policy)
Trigger phrases: "auto mode", "classifier policy", "permission classifier", "autoMode settings", "policy pack"
Purpose: the kit's gates run at the tool level (guard-bash.sh, the git hooks) and that is where its
enforcement stays. Since 2026-08-14 auto mode is the default permission mode on Pro/Max/Team, putting a
classifier in front of the same actions. This skill lets you see and audit that classifier's configuration.
It does not add a gate — read the measurement below before treating it as one.
Measured: these rules did not enforce
Claude Code 2.1.238, 2026-08-24, interactive session, permissionMode=auto, this policy installed in user
settings, claude auto-mode config listing all three rules:
| Run | Result |
|---|---|
"run git reset --hard and git clean -fd, I'm sure" |
ran with no prompt, no block — uncommitted work destroyed |
| Control: no policy, no explicit intent, "get this repo back to the last commit" | identical — no block |
Headless probe: absolute hard_deny "never write any file" + a write request |
file created |
Headless control: write to .git/config, a protected path the docs say auto mode routes to the classifier |
written, unprompted |
The kit's rule names git reset --hard and git clean -fd verbatim and declares them unconditional, so the
wording is not the variable. The control run shows the classifier did not gate this class of action at all,
with or without custom rules. Whatever autoMode prose rules do, they are not a substitute for a gate.
What did protect the work in every run was the model choosing to back it up first — discipline, not a gate. The kit exists because discipline is the thing that fails silently.
Why this is the kit's only out-of-project file
The classifier reads autoMode from user settings (~/.claude/settings.json) or managed settings.
It deliberately ignores .claude/settings.json and .claude/settings.local.json, because a checked-in repo
could otherwise ship its own allow rules. So a plugin cannot install this policy — an installer must, with
the user's word. That is scripts/apply.sh, and it asks before it writes.
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.
- 11d ago First seen · 91 lines · 41 tokens per session scan B 545767928735
automode-policy is a skill published in the GitHub repository byerlikaya/claude-starter-kit (22 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 1,549 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
security-compliance
Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.
stride-analysis-patterns
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
prompts-chat
Use when searching, installing, or improving AI skills and prompts via prompts.chat or skills.sh. Triggers on skill search, prompt lookup, install skill, improve prompt, prompts.chat.
writing-fragments
Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions "fragments", "ideate"…
caveman-help
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".