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/ciscodevnet/essentials/mcp-hide-secretsnpx skills add CiscoDevNet/essentials --skill mcp-hide-secretsgit clone --depth 1 https://github.com/CiscoDevNet/essentialsWrote 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/ciscodevnet/essentials/mcp-hide-secrets)<a href="https://agentmods.dev/skills/ciscodevnet/essentials/mcp-hide-secrets"><img src="https://agentmods.dev/badge/skills/ciscodevnet/essentials/mcp-hide-secrets.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 | $0.00103 | $0.01272 |
| Opus 5 | $0.00051 | $0.00636 |
| Sonnet 5 | $0.00021 | $0.00254 |
| Haiku 4.5 | $0.00010 | $0.00127 |
Grade B, and why
mcp-hide-secrets 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 yesterday.
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.
scripts/run.sh fix-launchagents # sudo in Terminal when agent cannot prompt How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Hide Secrets (macOS — LaunchAgent + .env)
Move live credentials out of ~/.cursor/mcp.json and/or a project .cursor/mcp.json into ~/.local/share/cursor-mcp/mcp.env, loaded at login by a macOS LaunchAgent via launchctl setenv. Cursor interpolates ${env:VAR} in MCP env and headers blocks.
Agent workflow (required)
Run only scripts/run.sh. Do not write ad-hoc preflight, migrate, or verify commands.
# From this skill root (set PROJECT_MCP_JSON when a repo .cursor/mcp.json should be included):
chmod +x scripts/run.sh
USERNAME="$(whoami)" PROJECT_MCP_JSON="<repo>/.cursor/mcp.json" scripts/run.sh
USERNAME="$(whoami)" scripts/run.sh migrate
USERNAME="$(whoami)" scripts/run.sh status
scripts/run.sh fix-launchagents # sudo in Terminal when agent cannot prompt
Never read or display secret values from mcp.json or mcp.env. Report script output only.
| User says | Script |
|---|---|
/mcp-hide-secrets |
scripts/run.sh (default) |
/mcp-hide-secrets migrate |
scripts/run.sh migrate [optional mcp.json path] |
/mcp-hide-secrets status |
scripts/run.sh status |
/mcp-hide-secrets install |
scripts/run.sh install (after fix-launchagents) |
If sudo fails in a non-interactive shell, ask the user to run scripts/fix-launchagents-dir.sh in Terminal, then USERNAME="$(whoami)" scripts/run.sh install.
After success: user quits Cursor (Cmd+Q) and reopens from Dock.
MCP config targets
| Location | Path |
|---|---|
| Global | ~/.cursor/mcp.json |
| Project | <repo>/.cursor/mcp.json |
Both merge into ~/.local/share/cursor-mcp/mcp.env. Default run.sh migrates global first, then project when PROJECT_MCP_JSON is set. Migrate dirty files separately with scripts/run.sh migrate <path>.
Gotchas (keep in SKILL.md)
- Dock-launched Cursor does not see
~/.zshrcexports — session env via LaunchAgent is required. ~/Library/LaunchAgentsis sometimes owned byroot;fix-launchagents-dir.shis a normal step, not a one-off fix.- Migrate runs before LaunchAgent install so secrets move even when sudo is pending.
- A server named
github(any case) dropsheaderson migrate so OAuth can run.
What ships with it
16 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.
- LICENSE 11 KB
- references/install-cursor.md 1.5 KB
- references/launchagent-naming.md 1.4 KB
- references/launchctl.md 3.6 KB
- references/rationale.md 5.6 KB
- scripts/check-inline-secrets.py 1.6 KB runs code
- scripts/fix-launchagents-dir.sh 1.5 KB runs code
- scripts/install.sh 5.7 KB runs code
- scripts/lib.sh 819 B runs code
- scripts/load-mcp-env.sh 1.5 KB runs code
- scripts/local.your-username.cursor-mcp-env.plist 615 B
- scripts/mcp.env.example 501 B
- scripts/preflight.sh 1.7 KB runs code
- scripts/run.sh 3.1 KB runs code
- scripts/status.sh 1.3 KB runs code
- scripts/verify.sh 959 B runs code
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.
- yesterday First seen · 104 lines · 103 tokens per session scan B 85463bb7692b
mcp-hide-secrets is a skill published in the GitHub repository CiscoDevNet/essentials (7 stars, last pushed 17d ago), licensed Apache-2.0. It adds 103 tokens to every session and 1,272 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
frontmcp-guides
Tutorials, end-to-end walkthroughs, and complete reference projects for FrontMCP. Use when you want a getting-started guide, a full worked example, or to learn best practices by following a step-by-step build rather than a single API reference. Includes a beginner weather-API server (tool plus static resource, Zod…
create-skill
Create instruction-only skills that package knowledge and workflow guides for AI clients.
frontmcp-extensibility
Use when extending FrontMCP beyond the core SDK by integrating external npm packages, libraries, or third-party services into providers and tools. Covers VectoriaDB for in-memory semantic and vector search (ML-based embeddings or TF-IDF keyword engines, with persistence) and the tamper-evident, hash-chained skill…
incident-response-skill
A skill that uses object-style tool references with purpose descriptions and required flags, plus strict validation.
basic-inline-skill
A minimal instruction-only skill with inline content and the function builder alternative.
directory-based-skill
A skill loaded from a directory structure with SKILL.md frontmatter, plus file-based and URL-based instruction sources.