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/zhebil/claude-code-plugins/configure-auto-enrichnpx skills add zhebil/claude-code-plugins --skill configure-auto-enrichgit clone --depth 1 https://github.com/zhebil/claude-code-pluginsWrote 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/zhebil/claude-code-plugins/configure-auto-enrich)<a href="https://agentmods.dev/skills/zhebil/claude-code-plugins/configure-auto-enrich"><img src="https://agentmods.dev/badge/skills/zhebil/claude-code-plugins/configure-auto-enrich.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 | $0.00083 | $0.02754 |
| Opus 5 | $0.00042 | $0.01377 |
| Sonnet 5 | $0.00017 | $0.00551 |
| Haiku 4.5 | $0.00008 | $0.00275 |
Grade B, and why
configure-auto-enrich scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `cat "${CLAUDE_PLUGIN_DATA:-$HOME/.claude}/config.json" 2>/dev/null || cat "$HOME/.claude/auto-enrich.json" 2>/dev/null || echo "(no config file - defaults apply)"` How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
auto-enrich: explain + configure
User-invoked only. Don't run as a side effect of unrelated work. If the user mentions Jira / GitHub / GitLab / Sentry without asking to configure auto-enrich, ignore this skill.
What this skill does
Explain to the user what auto-enrich is, gather the current state in one pass (parallel CLI + auth + config checks), present a concise summary of "what's on, what's off, what you can change", and then act on whatever the user actually wants. Don't walk through numbered steps. Don't ask the user permission between every check. Don't re-prompt for things you can detect.
The user already triggered the skill because they want information. Lead with the explanation and the current state, not with questions.
The flow
1. Explain the plugin (short)
Open with a single tight paragraph. Cover:
- What it does: when the user submits a prompt mentioning a GitHub PR/issue/repo/file, GitLab issue/MR/project/file, Jira ticket, or Sentry issue, the plugin runs before Claude reads the prompt and prepends a compact markdown summary of that reference fetched via local CLIs (
gh,glab,acliorjira,sentry). GitHub file URLs (/blob/,/raw/,raw.githubusercontent.com) and GitLab file URLs (/-/blob/,/-/raw/) embed the file contents, with optional line anchors for slicing. - Why it needs CLI auth: the plugin doesn't store credentials. It just runs the CLIs as the user, so the CLIs need to be logged in to GitHub / GitLab / Atlassian / Sentry on their own. There's nothing to "configure" auth-wise inside the plugin.
- Code blocks are skipped: refs inside backticks or fenced blocks are never enriched.
- Each ref is enriched once per session (dedup state in
$CLAUDE_PLUGIN_DATA/seen.json, preserved across/compact).
Keep this to roughly 4-6 lines. Don't reproduce the README.
2. Gather current state in ONE parallel batch
Without asking, run the install + auth + config checks at the same time. Use a single tool message with parallel Bash calls. Don't do them sequentially and don't pause to confirm.
What ships with it
1 file 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.
- 6d ago First seen · 135 lines · 83 tokens per session scan B cca731c7bebc
configure-auto-enrich is a skill published in the GitHub repository zhebil/claude-code-plugins (7 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 2,754 once invoked, about $0.0004 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
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…
create-app
Guided journey from a raw app idea to a validated, cleanly architected first version that ships on a sustainable cadence. Orchestrates ten skills phase by phase - lean-startup, design-sprint, clean-architecture, domain-driven-design, clean-code, pragmatic-programmer, system-design, ios-hig-design, 37signals-way…
create-business
Guided journey from raw idea to a validated, positioned, priced business with a chosen beachhead. Orchestrates ten skills phase by phase - jobs-to-be-done, mom-test, design-sprint, lean-startup, good-strategy-bad-strategy, blue-ocean-strategy, obviously-awesome, hundred-million-offers, monetizing-innovation…
clean-architecture
Structure software around the Dependency Rule: source code dependencies point inward from frameworks to use cases to entities. Use when the user mentions "architecture layers", "dependency rule", "ports and adapters (hexagonal)", "onion architecture", "screaming architecture", "where should business logic go"…
cold-start-problem
Start and scale networked products using Andrew Chen's "The Cold Start Problem" framework for network effects. Use when the user mentions "network effects", "chicken and egg", "cold start", "two-sided marketplace", "atomic network", "hard side", "liquidity", "critical mass", "invite-only launch", "how do I get my…
influence-psychology
Apply the seven principles of ethical persuasion (reciprocity, commitment, social proof, authority, liking, scarcity, unity) to product design, copy, and sales. Use when the user mentions "social proof", "persuasive copy", "why users dont convert", "ethical persuasion", "reciprocity", "scarcity tactics", "commitment…