description: "Mandatory reflection and verification pass that emits an Accountability Report before every final output — stage 3 of the agentic workflow." kind: "package-bundle"

@javierfrancoleal/accountability-auditor

⚡ Super Agent Ready — part of the J.Franco governance layer for autonomous agents.

Created by J.Franco.

Summary

Stage 3 of the J.Franco agentic workflow:

Input → Detection (AI + human) → AI processes, decides, and proposes → Human reflects, verifies, and decides → Output

This plugin registers the accountability-auditor skill on the host skill registry. The skill teaches the agent to run a mandatory reflection and verification pass before every final output: audit the input trail (input-detector), the decision trail (decision-router), and the actions taken, then emit a compact Accountability Report the human reviews.

Use this plugin

In Desktop, open Plugins and enable Accountability Auditor. The skill appears in the session skill catalog; agents load it automatically before final outputs, and you can invoke it yourself by name to audit any previous work.

How it works

• lib/index.js registers a bundled skill provider on ctx.skills, following the @deepseek-ai/dsh-skill-badge provider pattern.
• assets/accountability-auditor.md holds the skill body.
• cordis.patch.yml inserts the provider row into the host plane of the Cordis tree, so its skills land in the global registry layer.

License

MIT — see the package license field.