Compare consecutive versions of one artifact with the defects found

baltor_iterative_improvement_record

Compare consecutive versions of one artifact with the defects found, the fix or reason for each and a severity-ordered before-and-after verdict, refusing a version that drops a recorded defect without a fix or a reason or claims a better verdict than the counts show.

Files, names only

LICENSE 1.0 KB
SKILL.md 1.7 KB
contracts/input.schema.json 3.3 KB
contracts/output.schema.json 5.0 KB
examples/example.expected.json 1.4 KB
examples/example.input.json 2.9 KB
references/README.md 3.7 KB
references/provenance.json 4.1 KB
scripts/tool.py 16.4 KB
verification/test_tool.py 13.5 KB

Full files in your harness.

What it takes and gives

Command: python3 -B scripts/tool.py < examples/example.input.json
Input fields: artifact_id, versions, resolutions, claimed_verdicts
Test: python3 -B -m unittest discover -s verification -p 'test_*.py' -v
Files: SKILL.md, contracts/input.schema.json, contracts/output.schema.json, scripts/tool.py
Placed for: Claude Code, Codex, OpenCode, Pi

Details

Kind: Skill
Licence: MIT
Declared effects: reads files, runs commands
Placed for: Claude Code, Codex, OpenCode, Pi
Source: docs/architecture/NORTH-STAR.md
Size: 10 files, 53.0 KB
Identity: baltor_iterative_improvement_record
Version: a899030fd913c8ae4a70a317801a4f8c14bace74fe54eff3284062baecb2a4c2

The version is the SHA-256 of the item your harness downloads; every file in it names its own checksum.

Where it is shown

Checks for agent workDeterministic skills

Related components

Something wrong with this item, its rights or its safety? Report it on the support page, or from your harness after a download.