Individual skill
grade-iterate
Use when a launched managed agent needs grading against a rubric and improving ('grade my agent', 'is it good enough'). Builds the outcome with outcome_builder.py, reads verdicts with verdict_reader.py and runs held-back evals from eval_scaffold.py.
agent-launcher/skills/grade-iterate/SKILL.md
Source commit 8f082544116fc0d014188e521ca40304cdfc86b0
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 10, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 29,605
- Repository last updated
- Nov 5, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agentic-ai Repository topic
- anthropic-claude Repository topic
- claude-ai Repository topic
- claude-code Repository topic
- claude-skills Repository topic
- claude-code-skills Repository topic
- ai-coding-agent Repository topic
- claude-code-plugins Repository topic
- developer-tools Repository topic
- openai-codex Repository topic
- cma Declared skill tag
- outcome Declared skill tag
- rubric Declared skill tag
- grader Declared skill tag
- grade-iterate Declared skill tag
- loop Declared skill tag
- max-iterations Declared skill tag
- eval Declared skill tag
- held-back Declared skill tag
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
README.mddoc · 997 bytesSKILL.mdcore · 3,575 bytesSKILL.mdcore · 3,575 bytesSKILL.mdcore · 3,575 bytesSKILL.mdcore · 3,575 bytesscripts/eval_scaffold.pyruns · 3,870 bytesscripts/outcome_builder.pyruns · 3,735 bytesscripts/verdict_reader.pyruns · 4,283 bytes
Read excerpt
# Phase 3 — Grade → Iterate (the bounded loop)
This is the plugin's **loop**: CMA's `outcome` primitive self-grades the agent's
work in an isolated context and feeds failing verdicts back for the next attempt.
It is **always bounded** by `max_iterations` (1..20) — never "improve forever".
See [`../../references/loops-and-workflows.md`](../../references/loops-and-workflows.md)
and the outcome section of
[`../../references/cma-primitives.md`](../../references/cma-primitives.md).
## Workflow
1. **Define the outcome.**
```bash