harness-engineering

harness-engineering is a skill for Claude Code, Codex from navendubrajesh/context-management-for-agents. It costs 74 tokens per session (1,493 once invoked), scanned A, original, MIT.

A set of design rules for the operating loop around an autonomous software agent. It covers how the loop runs the agent, checks results, records activity, handles failures, and involves people.

In plain words
What is it for?
Use it to design agent execution loops, rollback and recovery, novelty checks that prevent repetition, human approval boundaries, durable logs, and fixed evaluation metrics.
Why use it?
It helps address unreliable or unsafe agent behavior by adding fixed checks, recovery steps, approval points, and records for later review.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for gstack. Also seen: built for gstack.

Good fit Use it to design agent execution loops, rollback and recovery, novelty checks that prevent repetition, human approval boundaries, durable logs, and fixed evaluation metrics.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/navendubrajesh/context-management-for-agents/harness-engineering
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add navendubrajesh/context-management-for-agents --skill harness-engineering
Clone the repo
git clone --depth 1 https://github.com/navendubrajesh/context-management-for-agents

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for harness-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/harness-engineering/github.svg)](https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/harness-engineering)
Your own site
<a href="https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/harness-engineering"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/harness-engineering/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for harness-engineering

Your own site · 80×15
<a href="https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/harness-engineering"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/harness-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,493 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00074 $0.01493
Opus 5 $0.00037 $0.00746
Sonnet 5 $0.00015 $0.00299
Haiku 4.5 $0.00007 $0.00149

Measured 11d ago against content hash 72a9dd49cb19, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

harness-engineering scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/harness-engineering/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Engineering for Autonomous Agents

Design the operating loop that wraps an autonomous agent — the harness that manages execution, evaluates outputs, enforces safety, and provides human oversight. A well-designed harness transforms an unreliable agent into a reliable system by adding deterministic guardrails around non-deterministic behavior. The harness is the engineering, the agent is the capability.

When to Activate

Activate this skill when:

  • Designing autonomous agent execution loops
  • Implementing rollback and recovery mechanisms for agent failures
  • Building novelty gates to prevent repetitive agent behavior
  • Defining human approval boundaries for high-risk agent actions
  • Designing durable logging for post-hoc analysis of agent behavior
  • Locking evaluation metrics to prevent metric gaming

Do not activate this skill for adjacent work owned by other skills:

  • Building evaluation checks and metrics: evaluation.
  • Implementing LLM-as-judge scoring: advanced-evaluation.
  • Designing multi-agent coordination protocols: multi-agent-patterns.
  • Building hosted sandbox infrastructure: hosted-agents.
  • Inline destructive-command warnings during an active session: GStack /careful, /freeze, /guard — use those for tactical safety; this skill designs the full harness loop.

Core Concepts

The harness is the deterministic wrapper around the non-deterministic agent. It manages five concerns:

  1. Execution control — Start, pause, resume, and terminate agent sessions. Enforce time limits, token budgets, and action counts.
  2. Evaluation gates — Check agent outputs against quality criteria before accepting them. Gate on deterministic checks (format, constraints) and statistical checks (quality scores).
  3. Safety boundaries — Define actions that require human approval (destructive operations, external communications, resource-intensive tasks). Block unauthorized actions.
  4. State management — Log all actions, tool calls, and decisions for debugging. Enable rollback to previous states when failures are detected.
  5. Novelty detection — Detect and prevent repetitive behavior loops where agents retry the same failed approach.

Read the full file on GitHub · 174 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 174 lines · 74 tokens per session scan A 72a9dd49cb19

Subscribe to this mod's changes

harness-engineering is a skill published in the GitHub repository navendubrajesh/context-management-for-agents (2 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 1,493 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens