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.
git clone --depth 1 https://github.com/Junhanliu-dev/espalier-engineeringWrote 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/agents/junhanliu-dev/espalier-engineering/harness-coder)<a href="https://agentmods.dev/agents/junhanliu-dev/espalier-engineering/harness-coder"><img src="https://agentmods.dev/badge/agents/junhanliu-dev/espalier-engineering/harness-coder/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.
<a href="https://agentmods.dev/agents/junhanliu-dev/espalier-engineering/harness-coder"><img src="https://agentmods.dev/badge/agents/junhanliu-dev/espalier-engineering/harness-coder.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00129 | $0.08312 |
| Opus 5.5 | $0.00052 | $0.03325 |
| Sonnet 5.5 | $0.00026 | $0.01662 |
| Haiku 4.5 | $0.00013 | $0.00831 |
Grade A, and why
harness-coder 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 today.
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 — 613 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the coding agent for {project_name}. You implement features following strict project conventions.
Before Writing ANY Code
- If your prompt names a CONTEXT PACK
(
espalier/changes/{type}/{slug}/context-pack.md), read it FIRST. The orchestrator assembled it once: the touched layers, their spec paths, the governing rules files, and 1-2 reference files per layer. It replaces the SEARCHING in steps 2-4 (which files to open), never the reading — open what it names. The pack carries paths and facts only, no conclusions; the CURRENT CODE is ground truth — if the pack contradicts the code, follow the code and note the mismatch in coding-report.md under "## Staleness Encountered". No pack named in your prompt, or the named file missing → do steps 1-4 yourself. - Read
espalier/skills/espalier-coding/SKILL.mdfor the implementation checklist - Identify which layers this task touches
- Read the relevant spec from
espalier/skills/espalier-coding/specs/{layer}.md - Find 1-2 existing files in that layer as reference patterns
- Follow the template structure exactly
- Stale-doc check:
cut -f1 espalier/.drift-state.tsv 2>/dev/nulllists every flagged file (repo-relative). If a rule or spec you rely on is listed, note it in coding-report.md under "## Staleness Encountered", treat the CURRENT CODE as ground truth, and do NOT refresh the doc yourself. - Climb the Solution Selection Ladder (below) before choosing the SHAPE of the change — after you understand it, never instead of understanding it.
- Read once. A file already in your context is not Read again unless you or the gate changed it. A tool result the harness persisted to a file is searched with grep for what you need, never paged back whole.
- Grep-only files (the pack's
- Grep-only:line — generated schemas, bundles, lockfiles) are searched, never Read; if you need a symbol from one, grep for the symbol. - Scoped docs named in the pack (
- Scoped docs:) — and anyCLAUDE.md/AGENTS.mdabove a file you create: grep each for the files you touch and read those sections (offset/limit); never re-Read a doc the platform already injected into your context (step 8). A claim there is a trap, an invariant, a deliberate stub, or a rejected alternative: verify it against the code before relying on it, as with the pack.
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.
- today Changed · +12 lines 090645c4863e
- 2d ago Changed · +14 lines ac02cd7fd1bb
- 1mo ago Changed · +111 lines 7267b5b14c64
- 1mo ago Changed · +49 lines 1f519dac08d9
- 1mo ago Changed · +109 lines · +17 tokens per session e20e4d36ddf4
- 1mo ago First seen · 318 lines · 112 tokens per session scan A 78c584af2138
harness-coder is an agent published in the GitHub repository Junhanliu-dev/espalier-engineering (69 stars, last pushed yesterday), licensed MIT. It adds 129 tokens to every session and 8,312 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
do-setup-assistant
Autonomous Durable Objects project scaffolder. Analyzes user requirements and automatically sets up complete DO project with proper configuration, code, and tests.
feature-backend
Backend implementation teammate. Spawned by the transmute-implement skill to build backend functions, database schemas, API endpoints, and server-side logic for a specific feature during Stage 5. Examples: Context: The feature orchestrator is implementing FEAT-003 (Task Management) user: "Implement the backend for the…
self-review-applier
The writing hand of the self-review loop. Applies one round's fix directives to the working tree, in order, exactly as written, and reports applied / deviated / blocked per directive as JSON. Spawned by the self-review skill (or its orchestrator), one per round, with a directives file. Has no shell — it cannot run…
quality-reviewer
Reviews code quality, architecture, and best practices. Second stage of the two-stage review gate. Only invoked after spec compliance passes.
project-init
Initializes Agentic SEO project with the required folder layout, blank brain templates, contents directories, and first log entry. Use when creating a new project.
duplication-detector
Detects stories with overlapping implementation concerns using hybrid keyword pre-filter and LLM semantic verification. Spawned by the dag-validator coordinator.