unifi-mcp: Skill for Claude Code

.agents/skills/mcp-response-redaction-governance/SKILL.md

myco:mcp-response-redaction-governance is a skill for Claude Code from sirkirby/unifi-mcp. It costs 215 tokens per session (3,305 once invoked), scanned A, original, MIT.

A set of rules for controlling when MCP tools and API responses may reveal sensitive fields such as secrets, tokens, or credentials.

In plain words
What is it for?
Use it when adding or reviewing sensitive-field redaction on UniFi Network, Access, Protect, or API surfaces.
Why use it?
It prevents a caller's request for raw data from being treated as permission to disclose protected information.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is sirkirby/unifi-mcp's own configuration. It tells Claude Code how to work on unifi-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything unifi-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sirkirby/unifi-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sirkirby/unifi-mcp/main/.agents/skills/mcp-response-redaction-governance/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sirkirby/unifi-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for myco:mcp-response-redaction-governance

README.md
[![agentmods](https://agentmods.dev/badge/skills/sirkirby/unifi-mcp/mcp-response-redaction-governance/github.svg)](https://agentmods.dev/skills/sirkirby/unifi-mcp/mcp-response-redaction-governance)
Your own site
<a href="https://agentmods.dev/skills/sirkirby/unifi-mcp/mcp-response-redaction-governance"><img src="https://agentmods.dev/badge/skills/sirkirby/unifi-mcp/mcp-response-redaction-governance/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.

agentmods 80×15 button for myco:mcp-response-redaction-governance

Your own site · 80×15
<a href="https://agentmods.dev/skills/sirkirby/unifi-mcp/mcp-response-redaction-governance"><img src="https://agentmods.dev/badge/skills/sirkirby/unifi-mcp/mcp-response-redaction-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 215 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,305 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00215 $0.03305
Opus 5 $0.00108 $0.01653
Sonnet 5 $0.00043 $0.00661
Haiku 4.5 $0.00021 $0.00331

Measured 5d ago against content hash c64e4d0879ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

myco:mcp-response-redaction-governance 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 5d 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.

.agents/skills/mcp-response-redaction-governance/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Response Redaction Governance

This domain covers how sensitive-field disclosure (secrets, tokens, raw credentials) is controlled across MCP tools and API responses. The governing principle: request intent is not authorization. A caller argument like include_sensitive=true expresses what the caller wants, but only server/operator policy decides whether to honor it. Never let a per-call argument directly gate secret disclosure.

Prerequisites

  • Know which surface you're touching: an MCP product server (network/access/protect) or the REST API (api). Each surface has its own env-var prefix and resolves the redaction decision at a different point in the request lifecycle (see Procedure A).
  • Do not assume a single unified "PolicyEngine" class exists. Check packages/unifi-core/src/unifi_core/policy.py and packages/unifi-core/src/unifi_core/policy_gate.py directly — there are two separate mechanisms, not one (see Procedure B).
  • Locate the correct enforcement point for what you're changing: read-path redaction and the mutation write-back guard are two different checks in two different files (see Procedure C). Don't assume one covers the other.

Procedure A: Configuring redaction policy per surface

Sensitive-field disclosure is controlled by a boolean, named for the enforced behavior rather than a data format:

policy:
  response:
    redact_sensitive_fields: true  # default; true = redact secrets

Naming rationale: redact_sensitive_fields: true|false is clearer than alternatives like sensitive_fields: redacted|raw, because the operator is deciding whether the server redacts, not choosing an output format. Keep this convention when adding new redaction toggles.

The boolean is resolved by should_redact_sensitive_fields(server_prefix, config, env) in packages/unifi-core/src/unifi_core/policy.py, in this order (highest specificity wins):

  1. UNIFI_{SURFACE}_REDACT_SENSITIVE_FIELDS — per-surface env override (e.g. UNIFI_NETWORK_REDACT_SENSITIVE_FIELDS, UNIFI_API_REDACT_SENSITIVE_FIELDS)
  2. UNIFI_REDACT_SENSITIVE_FIELDS — global env fallback
  3. policy.response.redact_sensitive_fields from the surface's own config
  4. Default: true (redact) if nothing is set — safe-by-default

Read the full file on GitHub · 278 lines

Changes

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.

  1. 5d ago Changed · +17 lines c64e4d0879ac
  2. 13d ago First seen · 261 lines · 215 tokens per session scan A 26eb13a02da8

Subscribe to this mod's changes

myco:mcp-response-redaction-governance is a skill published in the GitHub repository sirkirby/unifi-mcp (809 stars, last pushed yesterday), licensed MIT. It adds 215 tokens to every session and 3,305 once invoked, about $0.0011 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

n8n-code-tool

Write JavaScript or Python for the n8n Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode) — the AI-agent-callable tool, NOT the workflow Code node. Use when building a Code Tool attached to an AI Agent, writing code that an LLM will invoke, parsing the query input, returning a string result, defining an input schema…

czlonkowski/n8n-mcp · 221 tokens

n8n-subworkflows

Build reusable, composable n8n sub-workflows. Use when extracting shared logic, building anything multi-step or reused across workflows, or any workflow over 10 nodes — and whenever the user mentions sub-workflows, Execute Workflow, reuse, shared/common logic, modular workflows, "Define Below" inputs…

czlonkowski/n8n-mcp · 121 tokens

sanity-best-practices

Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, webhooks, Blueprints, and framework integrations such as Next.js, Nuxt, Astro, Remix, SvelteKit, Angular, Hydrogen, and the App SDK. Use this…

sanity-io/agent-toolkit · 164 tokens

tech-specs

To define clear, testable tech specs from requirements — target-state architecture, contracts, interfaces.

griddynamics/rosetta · 23 tokens

frontmcp-development

Use when building any FrontMCP server component other than a tool (for tools, use create-tool). Covers @Resource static resources and parameterized URI templates; @Prompt reusable prompts (RAG, multi-turn); @Provider singleton dependency-injection providers (database pools, API clients); @Agent autonomous LLM agents…

agentfront/frontmcp · 196 tokens

pipefy-api-fallback

Use this skill when an MCP tool fails AND the introspection skill could not resolve the problem. This is the last-resort fallback (Tier 3): call the Pipefy GraphQL API directly using curl or httpx, authenticating with the Service Account (OAuth2) or a Personal Access Token (PAT) available as env var. Follow the 3-tier…

pipefy/ai-toolkit · 86 tokens