A router for choosing one stage of a Harness Engineering workflow when a request could fit several stages. Harness Engineering here means organizing the lifecycle of building, reviewing, debugging, and maintaining agent-driven software work.

Use it when deciding whether to start, resume, plan, implement, review, debug, schedule a heartbeat, or clarify terminology in that workflow.

Ambiguous requests can send work to the wrong starting point or combine several stages incorrectly. The router applies defined rules and returns one next skill invocation.

he-router — Skill for Codex by jscraik

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 jscraik/Agent-Skills --skill harness-engineering-he-router

Clone the repo

git clone --depth 1 https://github.com/jscraik/Agent-Skills

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jscraik/agent-skills/harness-engineering-he-router/github.svg)](https://agentmods.dev/skills/jscraik/agent-skills/harness-engineering-he-router)

Your own site

<a href="https://agentmods.dev/skills/jscraik/agent-skills/harness-engineering-he-router"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/harness-engineering-he-router/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jscraik/agent-skills/harness-engineering-he-router"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/harness-engineering-he-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,381 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.

Model	Per session	Once invoked
Fable 5.1	$0.00038	$0.01381
Opus 5	$0.00019	$0.00691
Sonnet 5	$0.00008	$0.00276
Haiku 4.5	$0.00004	$0.00138

Measured 11d ago against content hash a83dc33c7ef9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

he-router 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.

Infrastructure/references/deferred-skill-context/harness-engineering-he-router/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness Engineering Router

Select exactly one harness-engineering stage and return one exact next skill invocation.

When To Use

No stage is explicit.
Multiple stages appear plausible.

Inputs

User request text.
Optional artifact paths.

Outputs

schema_version: 1 when structured output is requested.
One stage from ../../references/routing-map.json.
One rationale sentence and one exact next skill invocation.
One subagent plan with mapped roles, available/missing split, and fallback.
One confidence value (high, medium, or blocked) and one missing_input value when blocked.

Procedure

Parse direct he-* stage names, artifact state, lifecycle words, and risk words before choosing a stage because direct invocations and lifecycle state should beat broad keyword matches.
Apply the deterministic decision order in ../../references/deterministic-stage-routing.md because overlapping requests must route the same way every time.
Pick exactly one stage using the highest-priority matching rule from ../../references/routing-map.json; do not merge multiple stages into one response.
Route explicit domain-model, ubiquitous-language, CONTEXT.md, glossary, or terminology requests by artifact state: fuzzy idea to he-brainstorm, first contract to he-spec, existing spec conflict to he-deepen-spec, execution drift to he-work, review drift to a review stage.
Route recurring follow-up, monitor, heartbeat, loop, every <interval>, or until green/merged/done requests to he-heartbeat; he-heartbeat must select the underlying HE work/review/debug stage for each wake-up.
Route prior-session, archived-session, session-collector, repeated-failure, or "what keeps failing" requests with ../../references/session-evidence-contract.md: plugin/workflow improvement to he-improve, active lifecycle drift to he-compound-refresh, recurring waits to he-heartbeat, concrete derived tasks to he-work, and bug/root-cause evidence to he-fix-bugs.
Route QA session, conversational bug-report, or feedback-to-Linear requests by expected-behavior clarity: clear single/multiple defects to he-fix-bugs, unclear expected behavior to he-brainstorm or he-spec, issue-set sequencing to he-plan.
Resolve mapped roles from ~/.codex/agents/manifest.json, preferring he-* roles when available in the stage map.
Return outputs with selected_stage, matched_rule, confidence, rationale, next_invocation, and subagent policy fields.
If still ambiguous after applying the table, return blocked with exactly one missing input instead of guessing.

Read the full file on GitHub · 99 lines

Files

What ships with it

8 files 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.

11d ago First seen · 99 lines · 38 tokens per session scan A a83dc33c7ef9

Subscribe to this mod's changes

he-router is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 10d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,381 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.

Building agents Planning agent-skills agentic-workflow ai-agents ai-coding-agents ask-cli automation

he-router

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Harness Engineering Router

When To Use

Inputs

Outputs

Procedure

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

ad-creative

humanizer-zh

skill-creator

daily-brief

imf-data

scholar-research