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 deepklarity/harness-kit --skill hk-scout-wikigit clone --depth 1 https://github.com/deepklarity/harness-kitWrote 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/deepklarity/harness-kit/hk-scout-wiki)<a href="https://agentmods.dev/skills/deepklarity/harness-kit/hk-scout-wiki"><img src="https://agentmods.dev/badge/skills/deepklarity/harness-kit/hk-scout-wiki/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/deepklarity/harness-kit/hk-scout-wiki"><img src="https://agentmods.dev/badge/skills/deepklarity/harness-kit/hk-scout-wiki.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00114 | $0.00877 |
| Opus 5.5 | $0.00046 | $0.00351 |
| Sonnet 5.5 | $0.00023 | $0.00175 |
| Haiku 4.5 | $0.00011 | $0.00088 |
Grade A, and why
hk-scout-wiki 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 1mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scout wave → wiki → ideas (project-agnostic)
Three phases. Phases 1-2 are cheap (haiku); phase 3 needs judgment (sonnet or the main conversation). The wiki is evidence; the ideas are the product.
Phase 0 — Discover the project (once per session)
- Wiki root: existing
docs/wiki/(or wherever a wiki README already lives). None yet → createdocs/wiki/README.mdwith: a category table, the entry format below, and grep/tag conventions. Never a second format. - Project context: read the project's CLAUDE.md / roadmap / ideas file to learn (a) what the system IS in one line, (b) the named areas/buckets/ themes work is organized under, (c) where distilled ideas belong (an IDEAS/BRAINSTORM file, a backlog, or — if none — propose one). If the project defines a writing tone doc, read it and obey it.
Entry format (uniform, always)
# <Title>
source: <url>
author: <who> | fetched: <yyyy-mm> | status: read | unreachable
tags: <comma, separated, lowercase-hyphenated>
**One line.** <what you'd tell a colleague>
## TL;DR
3-6 plain sentences.
## Key ideas
Self-contained bullets.
## Project hooks
Where this touches THIS project: named areas, files, contradictions worth
arguing about. Honest "nothing yet" allowed.
Phase 1 — Scout (parallel haiku agents)
- Partition sources into batches of 4-8 by theme; each theme is a wiki
category directory with its own
TOC.md. Whole-blog surveys go insources/(survey = recurring theses + best posts, one line each). - Launch ALL batches as parallel haiku general-purpose agents in ONE
message. Every prompt includes: the entry format verbatim, the fetch
list, the project-context line from Phase 0, the unreachable rule
(retry once, then write the entry with
status: unreachable— NEVER invent content), and the order to write the categoryTOC.md(- [title](file.md) — one line. tags: ...). - No explicit link list ("trending X")? One haiku agent with WebSearch builds the URL list first; then partition.
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.
- 1mo ago First seen · 79 lines · 114 tokens per session scan A 4079c39c44f0
hk-scout-wiki is a skill published in the GitHub repository deepklarity/harness-kit (102 stars, last pushed 3mo ago), licensed MIT. It adds 114 tokens to every session and 877 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 skills, from other repositories
agent-benchmark-suite
Agent skill for benchmark-suite - invoke with $agent-benchmark-suite.
agent-crdt-synchronizer
Agent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer.
agent-performance-monitor
Agent skill for performance-monitor - invoke with $agent-performance-monitor.
agent-resource-allocator
Agent skill for resource-allocator - invoke with $agent-resource-allocator.
agent-topology-optimizer
Agent skill for topology-optimizer - invoke with $agent-topology-optimizer.
flow-nexus-platform
Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges.