agentleFS
Sign inStart free
apinizerapinizer/agentnizer-cookbook/.claude/skills/decisions/SKILL.md

decisions

Skill2 starsChanged 4 months agoMITView on GitHub

View chief_architect autonomous escalation decisions for the current week or filtered window.

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-help, browser-harness and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • attentiondotnetSkill

    setup-help

    Walk the user through setting up anything step by step. Use when the user asks for help setting up, configuring, installing, or getting something working — "help me set up X", "walk me through this", "setup-help". Differentiator: gives one current step at a time, then always lists every remaining setup step after each response.

    Also in 3 projects that use this

  • itgoyoSkill

    browser-harness

    Direct browser control via CDP. Use when the user wants to automate, scrape, test, or interact with web pages. Connects to the user's already-running Chrome.

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

The file

Create a free account to mount
Files
SKILL.md

/decisions — chief_architect verdict archive

Round 4 introduced chief_architect, the 14th synchronous agent that fires on chief_architect_pending and emits a structured 7-verdict decision.json. Each decision is appended to a weekly archive at .state/decisions-archive/decisions-YYYY-WW.jsonl. This skill is the read-only viewer.

Usage

/decisions                          # current week summary
/decisions --week 2026-W19          # specific ISO week
/decisions --verdict scope_reduce   # filter by verdict
/decisions --task <task-id>         # all decisions for one task

What it shows

  • Verdict distribution histogram — counts per verdict (resurrect, scope_reduce, decompose_again, skip, skip_with_warning, terminal_fail, await_user_info).
  • Last 5 decision.md samples — short rationale excerpts.
  • Manifesto-axis breakdown — which axis (Performance / Thread Safety / Safety / Observability / Human-in-the-loop) the chief_architect cited most often when escalating.

When useful

  • Audit — review what the autonomous escalator actually decided during a week of operation; spot decisions that should have been human-reviewed instead.
  • EU AI Act traceability — the archive plus per-decision rationale satisfies Article 12 logging requirements out-of-the-box.
  • Tuner input — recurring terminal_fail verdicts on the same module signal an escalation tree gap the weekly tuner should address.

Backend implementation

tail -n 200 .state/decisions-archive/decisions-2026-W19.jsonl \
  | jq 'select(.verdict == "scope_reduce") | {task_id, rationale_summary}'

Notes

The archive is append-only. Decisions are never rewritten or deleted — even when a resurrect verdict ultimately fails, the original decision stays for the audit trail.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free