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 loulanyue/awesome-claude-notes --skill agent-harness-constructiongit clone --depth 1 https://github.com/loulanyue/awesome-claude-notesWrote 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/loulanyue/awesome-claude-notes/agent-harness-construction)<a href="https://agentmods.dev/skills/loulanyue/awesome-claude-notes/agent-harness-construction"><img src="https://agentmods.dev/badge/skills/loulanyue/awesome-claude-notes/agent-harness-construction/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/skills/loulanyue/awesome-claude-notes/agent-harness-construction"><img src="https://agentmods.dev/badge/skills/loulanyue/awesome-claude-notes/agent-harness-construction.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 | $0.00025 | $0.00507 |
| Opus 5 | $0.00013 | $0.00253 |
| Sonnet 5 | $0.00005 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
agent-harness-construction 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 8d 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.
This is a copy
92% identical to agent-harness-construction — 35 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Harness Construction
Use this skill when you are improving how an agent plans, calls tools, recovers from errors, and converges on completion.
Core Model
Agent output quality is constrained by:
- Action space quality
- Observation quality
- Recovery quality
- Context budget quality
Action Space Design
- Use stable, explicit tool names.
- Keep inputs schema-first and narrow.
- Return deterministic output shapes.
- Avoid catch-all tools unless isolation is impossible.
Granularity Rules
- Use micro-tools for high-risk operations (deploy, migration, permissions).
- Use medium tools for common edit/read/search loops.
- Use macro-tools only when round-trip overhead is the dominant cost.
Observation Design
Every tool response should include:
status: success|warning|errorsummary: one-line resultnext_actions: actionable follow-upsartifacts: file paths / IDs
Error Recovery Contract
For every error path, include:
- root cause hint
- safe retry instruction
- explicit stop condition
Context Budgeting
- Keep system prompt minimal and invariant.
- Move large guidance into skills loaded on demand.
- Prefer references to files over inlining long documents.
- Compact at phase boundaries, not arbitrary token thresholds.
Architecture Pattern Guidance
- ReAct: best for exploratory tasks with uncertain path.
- Function-calling: best for structured deterministic flows.
- Hybrid (recommended): ReAct planning + typed tool execution.
Benchmarking
Track:
- completion rate
- retries per task
- pass@1 and pass@3
- cost per successful task
Anti-Patterns
- Too many tools with overlapping semantics.
- Opaque tool output with no recovery hints.
- Error-only output without next steps.
- Context overloading with irrelevant references.
原文
ナビゲーション
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.
- 8d ago First seen · 83 lines · 25 tokens per session scan A 62bfd5ab829e
agent-harness-construction is a skill published in the GitHub repository loulanyue/awesome-claude-notes (270 stars, last pushed 9d ago), licensed MIT. It adds 25 tokens to every session and 507 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to agent-harness-construction, differing in 35 lines, and is treated as a copy.
Other skills, from other repositories
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
loop
Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…
council
Full execution protocol for MODE: COUNCIL -- General Council research, parallel member dispatch, disagreement handling, and synthesis.
safe-extraction
Apply when extracting code from a large monolith file into submodules. Covers barrel re-exports, internals DI seam proxy patterns, CI invariant allowlist updates, and cross-file test verification. Prevents CI failures, broken imports, and test regressions from code extraction.
bundle-safety
Bundle transform safety — minification variant selection, consumer-constraint verification, identifier preservation, and namespace re-export coverage for build output.
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…