harness-review SKILL.md skillA
harness-review from naman10parikh/agentgrid is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add naman10parikh/agentgrid/harness-review@git:20260526.f887f6cPins git:20260526.f887f6c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- naman10parikh/agentgrid
- Path
.claude/skills/harness-review/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260526.f887f6c, committed May 26, 2026
- Size
- 1,622 bytes
- Repository stars
- 9
- License
- MIT
Review an agent's harness (scaffold) for quality, token efficiency, and correctness. Based on harness engineering research.
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
## The Core Insight Same model with scaffold A scores 42%. Same model with scaffold B scores 78%. The harness IS the product. ## Review Checklist ### 1. Context Loading - [ ] Bootstrap memory under 2,000 tokens? - [ ] Skills loaded on-demand, not all upfront? - [ ] Total input under 40% of context window? (the "dumb zone" is past 60%) ### 2. Tool Design - [ ] Each tool has a clear, one-sentence description? - [ ] Failed tool calls return actionable error messages (not stack traces)? - [ ] Tool results are concise (no dumping raw HTML/JSON)? ### 3. Error Recovery - [ ] Retry logic with exponential backoff? - [ ] Graceful degradation (if tool X fails, try alternative)? - [ ] Never silent swallowing of errors? ### 4. Model Routing - [ ] Parsing/extraction tasks → cheapest tier (Haiku)? - [ ] Reasoning/planning → middle tier (Sonnet)? - [ ] Architecture/complex decisions → top tier (Opus)? - [ ] Never sending 100K tokens to the expensive model? ### 5. Memory Management - [ ] Important facts written to disk BEFORE compaction? - [ ] Memory files have clear structure (not just append-only)? - [ ] Cross-session memory actually loads at session start? ### 6. Planning …
Read the whole file at its exact version.
How to install
mdr add naman10parikh/agentgrid/harness-review@sha256:aa18afe31d96162fThe line at the top of this page pins the label git:20260526.f887f6c, 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_h6ek6nhu5n7usvb4)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on May 26, 2026.
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 (1622 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
naman10parikh/agentgrid · 9 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_h6ek6nhu5n7usvb4 GET https://markdownregistry.com/api/v1/resolve?ref=naman10parikh/agentgrid/harness-review GET https://markdownregistry.com/api/v1/blob/aa18afe31d96162f2bd4a6667d40a97a10738a3de765880972dff92bab9d81d2
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.
More from naman10parikh/agentgrid
Every file in naman10parikh/agentgrid