grade-iterate SKILL.md skillA
grade-iterate from alirezarezvani/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add alirezarezvani/claude-skills/grade-iterate@v2.11.2Pins v2.11.2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- alirezarezvani/claude-skills
- Path
agent-launcher/skills/grade-iterate/SKILL.md- Versions recorded
- 4
- Latest version
- v2.11.2, committed Oct 21, 2026
- First version recorded
- Aug 17, 2026
- Size
- 4,179 bytes
- Repository stars
- 29,490
- License
- MIT
Phase 3 of building a Claude Managed Agent — the bounded grade→iterate loop. Define a CMA outcome (a required markdown rubric graded by an isolated grader), read each verdict, decide the next move (sharpen / re-run / promote to schedule), and once a version passes, run held-back eval cases in parallel. Use when the user says "grade my agent", "make it pass the rubric", "iterate until it's good", "is it good enough", or when the orchestrator routes phase=grade-iterate. outcome_builder.py builds…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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
python3 scripts/outcome_builder.py \
--sheet ./my-agent/build-sheet.json --max-iterations 5 \
--out ./my-agent/payloads/outcome.json
```
The **rubric is required**; `max_iterations` is clamped to 1..20. Send the
payload as a `user.define_outcome` event (append to the running session).
2. **Read every verdict first.**
```bash
python3 scripts/verdict_reader.py --result ./my-agent/last-verdict.json
```
Tables the rubric outcome and recommends: **SHIP** (`satisfied`), **SHARPEN**
then re-run (`needs_revision`), **ESCALATE** (`max_iterations_reached` /
…Read the whole file at its exact version.
How to install
mdr add alirezarezvani/claude-skills/grade-iterate@sha256:601c5e8d006179d4The line at the top of this page pins the label v2.11.2, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_vryq27dzl6vpgrhb)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Aug 17, 2026 and Oct 21, 2026, about one every 22 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v2.11.2 latest | 2026-10-21 | 74fa5ea | 4,179 B | A | view · diff |
| v2.11.2 | 2026-08-24 | 86beb8f | 4,161 B | A | view · diff |
| v2.11.2 | 2026-08-24 | 9ceecb1 | 4,212 B | A | view · diff |
| v2.12.0 | 2026-08-17 | d1f2396 | 4,212 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4179 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
alirezarezvani/claude-skills · 29,490 stars · license MIT · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_vryq27dzl6vpgrhb GET https://markdownregistry.com/api/v1/resolve?ref=alirezarezvani/claude-skills/grade-iterate GET https://markdownregistry.com/api/v1/blob/601c5e8d006179d4f0647019a99f8471164aaa955aab0302857a041400b09890
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.