agent-harness SKILL.md skillA

agent-harness from ssheleg/agent-stack is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add ssheleg/agent-stack/agent-harness@git:20261028.52b0584

Pins git:20261028.52b0584 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
ssheleg/agent-stack
Path
plugins/agent-stack/skills/agent-harness/SKILL.md
Versions recorded
5
Latest version
git:20261028.52b0584, committed Oct 28, 2026
First version recorded
Oct 9, 2026
Size
14,244 bytes
Repository stars
4
License
MIT

Use when deciding an agent's system prompt and tools, not how its loop is wired: system prompt, tool choice, workflow or agent, harness audits. Triggers: "system prompt" / "системный промпт", "аудит агента". Not for the loop (agent-orchestrator), evals (agent-evals) or protocols (agent-interop).

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

# Agent harness — what the agent is told, and how to audit what someone else told theirs

`agent-orchestrator` wires the loop. `agent-evals` proves it behaves. `agent-interop` gets
it talking to other processes. **This skill is the layer between them and the model: the
prompt, the tools, and the choice of technique.** Harness engineering includes
context management as well as instructions. Its effect depends on the task,
model and evaluation; benchmark gains do not establish a universal improvement.

It runs in both directions. Building one and auditing one are the same checklist read
forwards and backwards, which is why they live together here.

---

## Triggers

"tool description", "agent loops forever", "prompt engineering", "harness engineering", "ReAct loop", "react pattern", "static or dynamic", "embed an agent", "agent SDK", "Pi harness", "встроить агента".

Moved here from the description in 0.31.3: "agent picks the wrong tool", "агент не
вызывает тул", "audit this agent".

## Rule zero — check the prompt first (a diagnostic heuristic, with exceptions)

For failures in tool selection or usage, inspect instructions and descriptions
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ssheleg/agent-stack/agent-harness@sha256:4b45a4114b5b37df

The line at the top of this page pins the label git:20261028.52b0584, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_niffaqxe7u2i5y34.svg)](https://markdownregistry.com/a/art_niffaqxe7u2i5y34)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Oct 9, 2026 and Oct 28, 2026, about one every 5 days.

versioncommittedcommitsizeaudit
git:20261028.52b0584 latest2026-10-28 52b0584 14,244 BA view · diff
git:20261025.28a03032026-10-25 28a0303 14,239 BA view · diff
git:20261020.672d5ff2026-10-20 672d5ff 14,278 BA view · diff
git:20261012.96ed0f82026-10-12 96ed0f8 14,571 BA view · diff
git:20261009.b512cb42026-10-09 b512cb4 14,596 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (14244 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

GitHub

ssheleg/agent-stack · 4 stars · license MIT · pushed 2026-11-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_niffaqxe7u2i5y34
GET https://markdownregistry.com/api/v1/resolve?ref=ssheleg/agent-stack/agent-harness
GET https://markdownregistry.com/api/v1/blob/4b45a4114b5b37df33f745031a8f5a8e98e09ceb98f64bed0dbdbeb117bc25b7

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 ssheleg/agent-stack

agent-evals SKILL.md skill
ssheleg/agent-stack · plugins/agent-stack/skills/agent-evals/SKILL.md · Use when measuring whether an agent works: eval suites, trajectory judging, traces as regression fixtures, a calibrated…
git:20261025.28a0303 · audit A · 4 stars
agent-interop SKILL.md skill
ssheleg/agent-stack · plugins/agent-stack/skills/agent-interop/SKILL.md · Use when an agent speaks MCP, A2A or a gateway beyond its process: MCP server or client, agent cards, MCP Registry…
git:20261028.52b0584 · audit A · 4 stars
agent-orchestrator SKILL.md skill
ssheleg/agent-stack · plugins/agent-stack/skills/agent-orchestrator/SKILL.md · Use when building an agent system (orchestrator, pipeline) or metering LLM spend. Triggers: "agent system" / "агентная…
git:20261025.28a0303 · audit A · 4 stars

Every file in ssheleg/agent-stack

Other files named agent-harness

agent-harness SKILL.md skill
alirezarezvani/claude-skills · .gemini/skills/agent-harness/SKILL.md
git:20260717.3691fcf · audit C · 29,490 stars
agent-harness SKILL.md skill
borghei/claude-skills · engineering/agent-harness/SKILL.md · Test and evaluation harness for AI agents — scenario suites, deterministic replay, regression diffing, cost and latency…
v1.0.0 · audit A · 1,075 stars

Browse by kind, by grade A, or by owner.