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/mertjane/awesome-claude-commandsWrote 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/mertjane/awesome-claude-commands/env-audit)<a href="https://agentmods.dev/commands/mertjane/awesome-claude-commands/env-audit"><img src="https://agentmods.dev/badge/commands/mertjane/awesome-claude-commands/env-audit/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/mertjane/awesome-claude-commands/env-audit"><img src="https://agentmods.dev/badge/commands/mertjane/awesome-claude-commands/env-audit.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 | $0.00038 | $0.01206 |
| Opus 5.5 | $0.00015 | $0.00482 |
| Sonnet 5.5 | $0.00008 | $0.00241 |
| Haiku 4.5 | $0.00004 | $0.00121 |
Grade A, and why
env-audit scanned grade A with 0 findings 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 2mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Environment Variables Audit
Audit the project's environment variable files and produce a report covering missing variables, undocumented extras, and security risks.
If $ARGUMENTS is provided, use it as the path to the active env file. Otherwise auto-detect.
Step 1 — Find Environment Files
Example/template file (source of truth) — search in order:
.env.example.env.sample.env.template.env.defaults
If none found, report: "No .env.example found. Cannot perform comparison audit. Consider creating one." Then continue with security-only audit of the active env file.
Active env file — search in order:
$ARGUMENTS(if provided).env.local.env.env.development.env.development.local
If no active env file found, report it and stop.
Step 2 — Parse Both Files
Read each file line by line:
- Skip blank lines and lines starting with
# - Split on first
=: key is everything before, value is everything after - Strip surrounding quotes from values (
"value"→value,'value'→value) - Collect:
{ key, value, hasValue: value.trim() !== "" }
Step 3 — Compare Keys
Missing variables (in example but not in active env):
- Key exists in example but not in active env
- Severity: ERROR — app likely broken without these
Undocumented extras (in active env but not in example):
- Key exists in active env but not in example
- Severity: WARNING — should be added to .env.example (without the value)
Empty variables (key exists in active env but value is blank):
- Key present but value is empty string
- Severity: WARNING if key looks important (contains SECRET, KEY, TOKEN, PASSWORD, URL, HOST)
Step 4 — Security Risk Analysis
For every variable in the active env file, check:
Hardcoded weak secrets:
- Key contains:
SECRET,KEY,TOKEN,PASSWORD,PASS,PWD,AUTH,CREDENTIAL - AND value matches any of:
secret,password,123456,test,dev,development,changeme,example,placeholder,your_*,replace_*,xxx,todo- Value shorter than 16 characters for secret/token fields
- Severity: HIGH — replace with a strong random value
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.
- 2mo ago First seen · 143 lines · 38 tokens per session scan A 36feda76433d
env-audit is a command published in the GitHub repository mertjane/awesome-claude-commands (2 stars, last pushed 8mo ago), licensed MIT. It adds 38 tokens to every session and 1,206 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
index-skills
Run the okhp3-skill-cataloger in full index mode to scan root-level family folders and generate SKILLS.md for the distribution surface.
catalog-skills
Run the okhp3-skill-cataloger to scan .agents/skills/ and regenerate the skills catalog README.
add-api-railway
Create a new Express API endpoint with full integration.
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.