Skip to content
cccskills
FreePublished on GitHub

plano-filter-guardrails

Review Plano filter chains for MCP setup, clear guardrail rejection messages, and safe ordering. The skill places safety checks before rewriting and enrichment, helping prevent costly processing of unsafe requests while preserving checks on allowed outputs.

OriginalShow the original description

Harden Plano filter chains and guardrails. Use for MCP filter setup, prompt guard responses, and safe filter ordering.

katanemo/plano7,101 stars(GitHub 7,101 + cccskills 0)

Run score Not tested

See how to install

Good for

  • Setting up MCP filters
  • Reordering a filter chain
  • Improving rejection messages
  • Checking safe and allowed prompts

Files included (1)

  • SKILL.md930 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Plano Filter Chains and Guardrails

Use this skill when safety controls or filter pipelines need correction.

When To Use

  • "Fix filter chain ordering"
  • "Set up MCP filters correctly"
  • "Improve guardrail rejection behavior"
  • "Harden request processing for safety"

Apply These Rules

  • filter-mcp
  • filter-guardrails
  • filter-ordering

Execution Checklist

  1. Configure filter type, transport, and tool explicitly for MCP.
  2. Ensure rejection messages are clear and actionable.
  3. Order chain as guards -> rewriters -> enrichment -> output checks.
  4. Prevent expensive enrichment on unsafe requests.
  5. Verify with representative blocked and allowed test prompts.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Builds the brightstaff native binary in release mode after code changes. If compilation fails, it diagnoses the build errors and fixes them so the binary can be produced.

  • Building brightstaff after changing its code
  • Diagnosing a failed brightstaff release build
  • Fixing compilation errors in brightstaff
katanemo/plano7.1KUpdated Oct 25, 2026

build-cli

FreeSummary

Build and install the `planoai` Python CLI locally after changes to its `cli/` code. It syncs the project dependencies, installs the package in editable mode, and checks that the command starts and displays its help.

  • Installing the CLI after editing its source
  • Checking that `planoai` starts and shows help
  • Diagnosing a local build or installation failure
katanemo/plano7.1KUpdated Oct 25, 2026

build-wasm

FreeSummary

Builds the Envoy WASM plugins for llm_gateway and prompt_gateway after code changes. If the build fails, it diagnoses and fixes the errors so the plugins can be compiled for the wasm32-wasip1 target.

  • Building Envoy WASM plugins after code changes
  • Compiling llm_gateway and prompt_gateway
  • Diagnosing failed WASM plugin builds
katanemo/plano7.1KUpdated Oct 25, 2026

check

FreeSummary

Check Rust changes by running formatting validation, Clippy linting, and library unit tests in order. It can fix formatting issues, asks for warnings to be resolved, and reports which checks passed or failed.

  • Checking Rust changes before review
  • Running formatting, lint, and unit checks
  • Finding code warnings after an edit
katanemo/plano7.1KUpdated Oct 25, 2026

new-provider

FreeSummary

Adds an AI provider to hermesllm by updating provider identifiers, parsing, request and response types when needed, model lists, and API mappings. It then runs the library tests to check that the changes compile and pass.

  • Integrating a new AI provider into hermesllm
  • Adding provider-specific API request and response types
  • Updating supported models and upstream API mappings
katanemo/plano7.1KUpdated Oct 25, 2026

Design advanced Plano architectures for distinct listeners and layered orchestration. Tighten prompt target schemas, reduce ambiguity in tool calls, and shape migration-safe recommendations with scenarios to check the design.

  • Planning a Plano system with multiple distinct listeners
  • Clarifying prompt target parameters and schemas
  • Combining model, prompt, and agent listeners
katanemo/plano7.1KUpdated Oct 25, 2026

See all skills by katanemo

Report a problem with this skill