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 chipi/agentic-ai-homelab --skill secrets-scangit clone --depth 1 https://github.com/chipi/agentic-ai-homelabWrote 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/chipi/agentic-ai-homelab/secrets-scan)<a href="https://agentmods.dev/skills/chipi/agentic-ai-homelab/secrets-scan"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/secrets-scan/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/chipi/agentic-ai-homelab/secrets-scan"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/secrets-scan.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 | $0.00088 | $0.00772 |
| Opus 5.5 | $0.00035 | $0.00309 |
| Sonnet 5.5 | $0.00018 | $0.00154 |
| Haiku 4.5 | $0.00009 | $0.00077 |
Grade B, and why
secrets-scan 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 17d 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.
wired in `~/.claude/settings.json` since 2026-07-30) blocks a `git commit`/`git push` from How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
secrets-scan
Catch secrets before they land in git. Enforces the non-negotiable: .env,
credentials, tokens, API keys — never in git, never in fixtures, never in a
commit message. Read-only — it never writes; it blocks by reporting.
Run
~/.claude/skills/secrets-scan/scripts/scan.sh # staged changes (what `git commit` would add)
~/.claude/skills/secrets-scan/scripts/scan.sh --push # commits not yet on the upstream (what `git push` sends)
~/.claude/skills/secrets-scan/scripts/scan.sh --range origin/main..HEAD
~/.claude/skills/secrets-scan/scripts/scan.sh --tree [PATH] # the working tree, no history
Run it from inside the repo.
- With gitleaks: gitleaks is used when installed, with ~200 provider rules. Findings are
listed
file:line — rule (commit …), with values redacted. - Without it: the script falls back to the same high-signal regexes as the hook below, and says so.
.env: a real.env(not.env.example) in the change is a finding by itself.
It ends with SECRETS SCAN: PASS/FAIL, exit 1 on FAIL.
The automatic net: the secrets-guard.sh PreToolUse hook (workstation/claude/hooks/,
wired in ~/.claude/settings.json since 2026-07-30) blocks a git commit/git push from
Claude whose change matches. Since 2026-10-17 it also runs gitleaks when installed. This script is
the on-demand report with file:line; ship runs it as its secrets gate.
Verified 2026-10-17:
- clean staged passes;
- a staged Stripe key, a bad commit range and a staged
.enveach FAIL with file:line or the file name; - without gitleaks, the regex fallback FAILs on an AWS key;
--tree workstation/claude/skillspasses.
Report
- End with
SECRETS SCAN: PASSorSECRETS SCAN: FAIL. - On FAIL, list each hit as
file:line — <rule>with the value redacted (never echo the secret). Tell the operator to remove it AND rotate — a secret committed to git is compromised even if later deleted. - Don't cry wolf on obvious placeholders:
buddy-is-the-king,hf_xxx…,<your-…>,${VAR},changeme,example, empty values. Note them as skipped.
What ships with it
2 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.
- 17d ago Changed · +13 lines scan A → B 9f390278001d
- 2mo ago First seen · 45 lines · 88 tokens per session scan A 3eafa11f7113
secrets-scan is a skill published in the GitHub repository chipi/agentic-ai-homelab (3 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 772 once invoked, about $0.0004 per session on Opus 5.5. 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
mikromcp
Use when managing, configuring, or troubleshooting MikroTik RouterOS devices through the MikroMCP server — picking the right tool, running safe (dry-run, confirmed, rollback-able) changes, fleet operations, and diagnosing network issues.
worker-integration
Worker-Agent integration for intelligent task dispatch and performance tracking.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
evo2-nim
Generate and analyze DNA sequences using NVIDIA's Evo 2 BioNeMo NIM microservice. Use for Evo2/Evo 2, DNA generation, genomic sequence generation, hosted generation, local Docker deployment, local forward passes, layer outputs, logits, sampled probabilities, and BioNeMo NIM workflows.