Skip to content

0xh3lios/dossier

v0.2.0CC0-1.0

A toolkit for building a model of a system, checking it with formal methods and keeping it current as the system changes. An agent drafts the specification and the models, then runs the checks. TLC, Apalache and Alloy, not the agent, decide whether each property holds. You read the result from the agent's account of what the system does, written as behaviors, where each claim is tied to the evidence for and against it. You review the specification and decide what a counterexample means.

GitHubOpen Website
skills

review

Give one behavior or a whole dossier an independent second read in a fresh context. Examine each claim against the evidence it maps to, test the scope of the explanation, and assess the formal abstraction and the recorded answers. Record the findings, and what was examined, in one review file. Use for a second opinion or an independent review. Not for adding claims, running new trials or making the owner's decisions.

Read SKILL.md at the source

Pinned to revision 9f94d71bb397, so it is the text this page describes rather than whatever the author pushed since.

Pre-approved tools experimental

Experimental field. Support varies between clients, so this list is what the author declared, not what your client will enforce.

  • Bash(dossier verify *)
  • Bash(dossier show *)
  • Bash(dossier where *)
  • Bash(dossier recheck *)
  • Bash(dossier review-basis *)

Files

Every link opens the file at its source, pinned to the revision this page describes.