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.
npx skills add Mark393295827/graph-engineering-architectures --skill harness-engineeringgit clone --depth 1 https://github.com/Mark393295827/graph-engineering-architecturesWrote 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.
[](https://agentmods.dev/skills/mark393295827/graph-engineering-architectures/harness-engineering)<a href="https://agentmods.dev/skills/mark393295827/graph-engineering-architectures/harness-engineering"><img src="https://agentmods.dev/badge/skills/mark393295827/graph-engineering-architectures/harness-engineering.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.01425 |
| Opus 5 | $0.00017 | $0.00713 |
| Sonnet 5 | $0.00007 | $0.00285 |
| Haiku 4.5 | $0.00003 | $0.00143 |
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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Engineering
<skill_contract> An agent workflow, runtime environment, tools, data sensitivity, effects, cadence, risk, and operator constraints. An auditable runtime kernel with scoped permissions, scheduling, observability, recovery, and eval controls. An end-to-end trace and failure-path tests prove bounded, replayable, recoverable delegated action. <non_goals>Business-task decomposition, prompt-only safety, broad credentials, or unbounded scheduled autonomy.</non_goals>
Treat the harness as the kernel around an LLM OS: context is RAM, durable state is disk, tools are system calls, skills are programs, the scheduler is control, and evals are verifiers. Load references/runtime-control-patterns.md for matrices and schemas.
Usage Template
Provide: workflow, users, agent roles, environment, tools/connections, data sensitivity, delegated actions, cadence, throughput/SLA, failure history, and risk tolerance.
Workflow
Run the trace gate: the harness must be able to show what the agent saw, decided, called, changed, and verified. Separate Agent (instructions/capabilities), Environment (network/files/credentials), and Session (mounted context/events/state). Define one auditable control path for high-risk intent and final joins.
<unknowns_gate>
If state ownership, credential scope, external side effects, retention, or approval authority is unclear, return NEEDS_INPUT. Probe tools with read-only discovery where possible; unknown side effects default to denied.
</unknowns_gate>
- Pass Four-C: Context truth/retrieval, Connections scoped accounts/APIs, Capabilities versioned skills/scripts/evals, Cadence trigger/receipt/anomaly/stop.
- Map runtime: stored program, control unit, hot context, durable disk, event bus, I/O tools, verifier, and garbage collector.
- Choose the lowest-context primitive: deterministic script/hook, skill, static Graph, connector, dynamic workflow, or agent team. Load capabilities lazily. Graph Engineering owns dependency semantics; the harness owns the ready queue, leases, duplicate delivery, concurrency, and executor health.
- Define each tool as a narrow system call with purpose, explicit inputs, bounds, timeout, idempotency, failure path, evidence, and audit location.
- Enforce least privilege in the environment, not only prose. Escalate autonomy through observe -> co-drive -> scoped reversible action -> monitored routine -> audited low-risk autonomy.
- For delegated action require mandate, scope, limit, preview, receipt, and rollback. Human approval governs irreversible/shared/financial/published/credentialed actions.
- Add deterministic feedback (tests, lint, LSP, policy checks) outside context when possible; add independent evaluator/red team for high-risk semantic output.
- Persist an append-only session event log and checkpoint; define alerts, fallback, incident response, cleanup, permission review, and stale-context/rule review.
- For scheduled work define Trigger, Context, Steering, Receipt, budget, stop, recovery, and executor health. A schedule firing is not task success.
- For Graph execution, persist node/edge/join transitions before releasing successors, make delivery idempotent, recover from the last verified checkpoint, and test permission denial, worker loss, duplicate events, and compensation without relying on in-memory scheduler state.
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.
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.
- 6d ago First seen · 114 lines · 34 tokens per session scan A 1f48e3c566a0
harness-engineering is a skill published in the GitHub repository Mark393295827/graph-engineering-architectures (2 stars, last pushed 16d ago), licensed MIT. It adds 34 tokens to every session and 1,425 once invoked, about $0.0002 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.
Other skills, from other repositories
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
python-package-management
Guide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use this when adding, modifying, or releasing packages.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
verify-samples-tool
How to use the verify-samples tool to run, verify, and manage sample definitions in the Agent Framework repository. Use this when adding, updating, or running sample verification.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.