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 S3YED/appie-kit --skill openrouter-key-managementgit clone --depth 1 https://github.com/S3YED/appie-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/s3yed/appie-kit/openrouter-key-management)<a href="https://agentmods.dev/skills/s3yed/appie-kit/openrouter-key-management"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/openrouter-key-management/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/s3yed/appie-kit/openrouter-key-management"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/openrouter-key-management.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 | $0.00044 | $0.02351 |
| Opus 5 | $0.00022 | $0.01175 |
| Sonnet 5 | $0.00009 | $0.00470 |
| Haiku 4.5 | $0.00004 | $0.00235 |
Grade D, and why
openrouter-key-management scanned grade D with 3 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
All keys on this fleet are tracked in `~/.weblyfe-secrets/orgo-openrouter-keys.env` (chmod 600, never git-tracked). Structure: Encoded or obfuscated payloadhighSupply chain
base64 or hex that is decoded and executed hides what actually runs from anyone reading the file.
ssh root@<host> 'echo c3lzdGVtY3RsIHJlc3RhcnQgaGVybWVzLWdhdGV3YXkK | base64 -d | bash' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import json, urllib.request How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenRouter Key Management
Use this skill when managing OpenRouter API keys across the fleet: checking per-key usage and limits, updating spending caps, restricting model access, setting up usage alerts, or creating/rotating keys.
Architecture
OpenRouter has two key-management mechanisms that stack:
- Per-key spending limits (
limitfield) — set on individual API keys via the Management API. Hard cap: requests are rejected when exceeded. - Guardrails (organization-level) — restrict models, providers, data retention per key or per member. Model allowlists, provider allowlists, and budget limits that layer on top of per-key limits (the lower limit wins).
Both require a Management API key — a special key type that can only manage keys, not make inference calls.
Key inventory and status check
All keys on this fleet are tracked in ~/.weblyfe-secrets/orgo-openrouter-keys.env (chmod 600, never git-tracked). Structure:
ORGO_APPIE6_FERDOWS=sk-or-...
OWN_APPIE1=sk-or-...
Check all keys' current status
Each key can query its own status (no Management key needed):
import json, urllib.request
keys = {
# Load from env file
}
base_url = "https://openrouter.ai/api/v1/key"
for name, api_key in keys.items():
req = urllib.request.Request(base_url)
req.add_header("Authorization", f"Bearer {api_key}")
with urllib.request.urlopen(req, timeout=10) as resp:
data = json.loads(resp.read())
d = data.get('data', {})
print(f"{name}: limit=${d.get('limit')}, "
f"remaining=${d.get('limit_remaining')}, "
f"usage=${d.get('usage',0):.4f}, "
f"reset={d.get('limit_reset')}")
Response fields on each key:
| Field | Type | Meaning |
|---|---|---|
limit |
number or null | Spending limit in USD (null = unlimited) |
limit_remaining |
number or null | Remaining credits for this period |
limit_reset |
"daily"/"weekly"/"monthly" or null | When limit resets |
usage |
number | Total credits used (all time) |
usage_daily/weekly/monthly |
number | Usage for current period |
disabled |
boolean | Whether the key is active |
include_byok_in_limit |
boolean | Whether BYOK usage counts toward limit |
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.
- 9d ago First seen · 222 lines · 44 tokens per session scan D ac3fa3393a4e
openrouter-key-management is a skill published in the GitHub repository S3YED/appie-kit (9 stars, last pushed 17d ago), licensed MIT. It adds 44 tokens to every session and 2,351 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, encoded or obfuscated payload, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
bim-cost-estimation-cwicr
Automated cost estimation from BIM models using DDC CWICR database (8 national bases, 78,228 positions). AI classification + vector search for accurate pricing.
cost-prediction
Predict construction project costs using Machine Learning. Use Linear Regression, K-Nearest Neighbors, and Random Forest models on historical project data. Train, evaluate, and deploy cost prediction models.
model-cost-compare
Trigger when the user asks which model to use, wants to compare model costs, says "what's cheapest for this task", "should I use Opus or Sonnet", "can a smaller model handle this", or "/model-cost-compare". Estimates token cost across Opus 4.6, Sonnet 4.6, GLM-5.1, Minimax M2.7, and local Gemma 4, then recommends the…
adaptive-wfo-epoch
Adaptive epoch selection for Walk-Forward Optimization. TRIGGERS - WFO epoch, epoch selection, WFE optimization, overfitting epochs.
opendeviation-eval-metrics
Machine-readable reference + computation scripts for state-of-the-art metrics evaluating open deviation bar (ODB, brim-to-brim price-based sampling) data.
ml-data-pipeline-architecture
Patterns for efficient ML data pipelines using Polars, Arrow, and ClickHouse. TRIGGERS - data pipeline, polars vs pandas, arrow format.