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/tranfu-labs/tranfu-skillsWrote 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/tranfu-labs/tranfu-skills/application-env)<a href="https://agentmods.dev/commands/tranfu-labs/tranfu-skills/application-env"><img src="https://agentmods.dev/badge/commands/tranfu-labs/tranfu-skills/application-env/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/tranfu-labs/tranfu-skills/application-env"><img src="https://agentmods.dev/badge/commands/tranfu-labs/tranfu-skills/application-env.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 | $0.00000 | $0.02080 |
| Opus 5 | $0.00000 | $0.01040 |
| Sonnet 5 | $0.00000 | $0.00416 |
| Haiku 4.5 | $0.00000 | $0.00208 |
Grade A, and why
application-env scanned grade A 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS \ How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Application Env 操作速查
reconcile Step 6I / 更新分支 C 用。Env 维度可独立增删改查,不需要重 PATCH 整个 application。
公共环境变量(同 application-crud.md):
BASE="http://120.77.223.183:8000"
APP_UUID="<application-uuid>"
列出现有 envs(reconcile Step 6 check)
curl -sS \
-H "Authorization: Bearer $COOLIFY_API_TOKEN" \
"$BASE/api/v1/applications/$APP_UUID/envs" \
| jq '[.[] | {uuid, key, value, is_literal}]'
返回数组,每条含 uuid(env 的)+ key + value + 几个 flag。
注意:value 在响应里是明文(除非 is_shown_once: true)——agent 看到也不要 echo / 不要写日志。
对比仓库 .env 与 Coolify 现状(reconcile Step 6 check)
必须 grep 过滤 Coolify 魔法变量前缀 (详见本文末尾"关于 Coolify 魔法变量"段), 否则每次都误诊 "Coolify 多了一堆 key":
MAGIC_PREFIXES='^(SERVICE_PASSWORD_|SERVICE_PASSWORDWITHSYMBOLS_|SERVICE_REALBASE64_|SERVICE_HEX_|SERVICE_FQDN_)'
REMOTE_KEYS=$(curl -sS -H "Authorization: Bearer $COOLIFY_API_TOKEN" \
"$BASE/api/v1/applications/$APP_UUID/envs" \
| jq -r '.[].key' \
| grep -vE "$MAGIC_PREFIXES" \
| sort)
LOCAL_KEYS=$(grep -v '^\s*#' .env | grep '=' | cut -d= -f1 \
| grep -vE "$MAGIC_PREFIXES" \
| sort)
echo "缺的 (本地有,Coolify 没):"
comm -23 <(echo "$LOCAL_KEYS") <(echo "$REMOTE_KEYS")
echo "多的 (Coolify 有,本地没):"
comm -13 <(echo "$LOCAL_KEYS") <(echo "$REMOTE_KEYS")
值的对比单独做(值不打印到屏幕,用文件 diff 或 hash 对比):
# 不打印明文,只显示哪些 key 的值不同
for key in $(comm -12 <(echo "$LOCAL_KEYS") <(echo "$REMOTE_KEYS")); do
local_val_hash=$(grep "^${key}=" .env | cut -d= -f2- | sha256sum | cut -c1-8)
remote_val_hash=$(curl -sS -H "Authorization: Bearer $COOLIFY_API_TOKEN" \
"$BASE/api/v1/applications/$APP_UUID/envs" \
| jq -r --arg k "$key" '.[] | select(.key==$k) | .value' \
| sha256sum | cut -c1-8)
[ "$local_val_hash" != "$remote_val_hash" ] && echo "$key: 不同 (本地 ${local_val_hash} vs Coolify ${remote_val_hash})"
done
创建一个 env(reconcile Step 6 act:补缺)
curl -sS -X POST \
-w "\nHTTP=%{http_code}\n" \
-H "Authorization: Bearer $COOLIFY_API_TOKEN" \
-H "Content-Type: application/json" \
-d "$(jq -nc --arg k "MY_KEY" --arg v "my_value" \
'{key: $k, value: $v, is_literal: true}')" \
"$BASE/api/v1/applications/$APP_UUID/envs"
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.
- 9d ago First seen · 170 lines · 0 tokens per session scan A 5c07fa13724a
application-env is a command published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,080 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.