agentsclimarketplace
Sign in

Case 02554

Skill knownasnaffy/prompthound/dataset/case_02554

Persona-weighted pre-send email governance for AI systems. Produces APPROVE/BLOCK/REWRITE decisions, writes decision artifacts to the board ledger, and returns strict machine-parseable JSON.From its SKILL.md

Install
npx -y skills add knownasnaffy/prompthound --skill case_02554

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.5 KB, 551 tokens by cl100k_base, as published. Nobody here has run it

consensus-send-email-guard

consensus-send-email-guard is a production-style outbound communication guardrail.

What this skill does

  • evaluates an email draft with a persona panel
  • aggregates votes by reputation (weighted approval policy)
  • enforces hard-block categories (sensitive data, legal/medical certainty, disallowed guarantees)
  • returns final decision: APPROVE | BLOCK | REWRITE
  • writes decision artifacts to board state

Why this matters

Email is high-impact and irreversible once sent. This skill reduces hallucinated promises and policy-violating claims before external side effects occur.

Ecosystem role

Stack position:

consensus-tools -> consensus-interact pattern -> persona_set -> send-email-guard

It converts raw generation into governed action with auditability.

Governance and learning

  • strict JSON contracts for automation pipelines
  • idempotent retries to prevent duplicate reputation mutation
  • reputation updates calibrate evaluator influence over time

Use cases

  • customer-facing outbound messaging
  • partner/legal-sensitive communications
  • automated campaign quality gates

Runtime, credentials, and network behavior

  • runtime binaries: node, tsx
  • network calls: none in guard decision logic
  • environment config read by this package: CONSENSUS_STATE_FILE, CONSENSUS_STATE_ROOT
  • filesystem writes: board/state artifacts under the configured consensus state path

Dependency trust model

  • consensus-guard-core is the first-party consensus package used in guard execution
  • versions are semver-pinned in package.json for reproducible installs
  • this skill does not request host-wide privileges and does not mutate other skills

Install

npm i consensus-send-email-guard

Quick start

node --import tsx run.js --input ./examples/email-input.json

Tool-call integration

This skill is wired to the consensus-interact contract boundary (via shared consensus-guard-core wrappers where applicable):

  • readBoardPolicy
  • getLatestPersonaSet / getPersonaSet
  • writeArtifact / writeDecision
  • idempotent decision lookup

This keeps board orchestration standardized across skills.

Invoke Contract

This skill exposes a canonical entrypoint:

  • invoke(input, opts?) -> Promise<OutputJson | ErrorJson>

invoke() starts the guard flow and executes deterministic policy evaluation with board operations via shared guard-core wrappers.

external_agent mode

Guards support two modes:

  • mode="external_agent": caller supplies external_votes[] from agents/humans/models for deterministic aggregation.
  • mode="persona": requires an existing persona_set_id; guard will not generate persona sets internally.

What ships with it: 13 files

25.3 KB alongside SKILL.md, 8 of them executable

examples/

src/

tests/

Keep looking

Skills are one crate of 326,834. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.