harness-improvement-loop SKILL.md skillB
harness-improvement-loop from tylerjrbuell/reactive-agents-ts is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add tylerjrbuell/reactive-agents-ts/harness-improvement-loop@git:20260722.cc051cfPins git:20260722.cc051cf in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- tylerjrbuell/reactive-agents-ts
- Path
.agents/skills/harness-improvement-loop/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260722.cc051cf, committed Jul 22, 2026
- First version recorded
- May 5, 2026
- Size
- 39,078 bytes
- Repository stars
- 31
- License
- MIT
Agentic harness diagnostic + improvement loop. Probes the framework with real model runs, uses the rax-diagnose CLI to root-cause failures from structured trace data, ships ONE coordinated architectural fix, verifies via before/after diff, commits with empirical evidence. Use at the start of any harness improvement session — replaces ad-hoc grep + log-spelunking with a deterministic feedback loop.
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
# Harness Improvement Loop
## What this is
A tight feedback loop for fixing harness failure modes using the framework's own diagnostic tooling (`@reactive-agents/diagnose`). Optimized for short iteration cycles — minutes per pass, not days. Every change lands with an empirical before/after trace as evidence.
```
Probe → Diagnose → Hypothesize → Fix → Verify → Commit
↑ │
└──────────────────────────────────────────────┘
iterate
```
This skill replaces the previous "wide-scan probe + giant report template" workflow. The diagnose CLI now does the heavy lifting that hand-rolled jq queries used to do.
## Prerequisites — the framework's diagnostic system
Tracing is **on by default** since Sprint 3.6. Every agent run writes a typed JSONL to `~/.reactive-agents/traces/<runId>.jsonl`. The `rax-diagnose` CLI is the primary inspection surface:
```bash
bun run rax:diagnose list # recent runs (most-recent first)
bun run rax:diagnose replay latest # pretty timeline of the most recent run
bun run rax:diagnose replay <runId> --only=verifier-verdict,harness-signal-injected
…Read the whole file at its exact version.
How to install
mdr add tylerjrbuell/reactive-agents-ts/harness-improvement-loop@sha256:499a19e0ce2a6136The line at the top of this page pins the label git:20260722.cc051cf, 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_7rm2ncbjtgib56gk)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between May 5, 2026 and Jul 22, 2026, about one every 19 days. Its first recorded version is graded A and its latest B.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260722.cc051cf latest | 2026-07-22 | cc051cf | 39,078 B | B | view · diff |
| git:20260711.e9d2266 | 2026-07-11 | e9d2266 | 35,045 B | B | view · diff |
| git:20260707.56e6e8e | 2026-07-07 | 56e6e8e | 34,821 B | B | view · diff |
| git:20260626.b55b67d | 2026-06-26 | b55b67d | 32,759 B | B | view · diff |
| git:20260505.72cf091 | 2026-05-05 | 72cf091 | 27,132 B | A | view |
Audit of the latest version
- fail: No link to a raw IP address (matched: http://127.0.0.1:8910)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (39078 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 script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
tylerjrbuell/reactive-agents-ts · 31 stars · license MIT · pushed 2026-10-28 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_7rm2ncbjtgib56gk GET https://markdownregistry.com/api/v1/resolve?ref=tylerjrbuell/reactive-agents-ts/harness-improvement-loop GET https://markdownregistry.com/api/v1/blob/499a19e0ce2a613643d0f6ebfdd38e84e8e338e01c16d2e8a86830edc1012139
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.