Agent Harness

What it does

When your agent uses it

• You want an agent
• Set up an agentic loop for marketing work
• Make the finance domain self-verifying)

Example prompts

• “s 18 domains (”
• “set up an agentic loop for marketing work”
• “make the finance domain self-verifying”
• “/agent-harness”

Requirements

• Python 3

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

1. 1Never adjudicate your own verification. verify runs the checks via subprocess;
2. 2Never modify a gate you are judged by. Check commands come from the manifest/plan.
3. 3One task at a time, writes serialized. Parallelize reading and judging, never two
4. 4Retry means a changed approach. Same command + same input = same failure. The retry
5. 5Budgets are terminal states, not suggestions. max_attempts_per_task → escalated
6. 6Fresh context beats long context. Every next directive is executable by a new
7. 7State lives in .agent-harness/ — never in .agenthub/, .autoresearch/, or
8. 8Plan and state files are a trust boundary. verify shell-executes each task's

What it can do on your machine

Read from SKILL.md and the folder at commit 19392f7. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/, which the agent can run.

  Shell commands in SKILL.md call:

  • python3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Harness loads about 2k tokens when it runs, and up to ~6.8k if it reads all its reference files. Until then it costs about 207 tokens; SKILL.md has 708 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~207

When it runs · the whole SKILL.md, loaded when a task matches

~2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~6.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from alirezarezvani/claude-skills at commit 19392f7, republished under its MIT licence (© alirezarezvani). 708 words, ~2,000 tokens.

name

agent-harness

description

Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).

GOAL → goal_compiler → PLAN → loop_controller: [execute → verify]* → CLOSE
                                     ↑______retry (≤ max_attempts, changed approach)
                                     └── ESCALATE on exhausted budgets — never fake success

# 0. Pick the domain manifest (18 committed under assets/harnesses/, e.g. engineering-team.json)
ls assets/harnesses/

# 1. Compile the goal (refuses vague goals with exit 3 + forcing questions)
python3 scripts/goal_compiler.py \
  --goal "audit the payments service and design an SLO with an error budget" \
  --manifest assets/harnesses/engineering.json --out plan.json

# 2. Initialize the loop state
python3 scripts/loop_controller.py init --plan plan.json --state .agent-harness/state.json

# 3. Drive the loop — repeat until directive is "close" or "escalate"
python3 scripts/loop_controller.py next --state .agent-harness/state.json
#    → {"action": "execute", "task": "T1", ...}: open the task's skill (SKILL.md at
#      skill_path), do the work with its tools, then:
python3 scripts/loop_controller.py record --state .agent-harness/state.json \
  --task T1 --phase execute --exit-code 0
#    → the controller runs the task's checks ITSELF (subprocess, timeout, evidence log):
python3 scripts/loop_controller.py verify --state .agent-harness/state.json --task T1 --cwd <repo-root>

# 4. Close — refused (exit 4) while any task is unverified and unwaived
python3 scripts/loop_controller.py close --state .agent-harness/state.json

python3 scripts/harness_manifest_builder.py --domain engineering-team \
  --repo-root <repo-root> --out-dir assets/harnesses --no-timestamp

© alirezarezvani, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 27 other files (scripts, references, assets) in engineering/agent-harness/skills/agent-harness of alirezarezvani/claude-skills.

• SKILL.md
• assets/harness_manifest.schema.json
• assets/harnesses/business-growth.json
• assets/harnesses/business-operations.json
• assets/harnesses/c-level-advisor.json
• assets/harnesses/commercial.json
• assets/harnesses/compliance-os.json
• assets/harnesses/engineering-team.json
• assets/harnesses/engineering.json
• assets/harnesses/finance.json
• assets/harnesses/loop-library.json
• assets/harnesses/markdown-html.json
• assets/harnesses/marketing-skill.json
• assets/harnesses/marketing.json
• assets/harnesses/product-team.json
• assets/harnesses/productivity.json
• assets/harnesses/project-management.json
• assets/harnesses/ra-qm-team.json
• assets/harnesses/research-ops.json
• … and 9 more

Open the folder on GitHubat commit 19392f7