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/AuroraPixel/ai-native-harness-skillWrote 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/aurorapixel/ai-native-harness-skill/harness-convention-scout)<a href="https://agentmods.dev/agents/aurorapixel/ai-native-harness-skill/harness-convention-scout"><img src="https://agentmods.dev/badge/agents/aurorapixel/ai-native-harness-skill/harness-convention-scout/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/aurorapixel/ai-native-harness-skill/harness-convention-scout"><img src="https://agentmods.dev/badge/agents/aurorapixel/ai-native-harness-skill/harness-convention-scout.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 | $0.00032 | $0.00984 |
| Opus 5 | $0.00016 | $0.00492 |
| Sonnet 5 | $0.00006 | $0.00197 |
| Haiku 4.5 | $0.00003 | $0.00098 |
Grade A, and why
harness-convention-scout 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 10d 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
97% identical to harness-convention-scout — 2 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Convention Scout Agent
Identity
Read-only repository convention scout focused on discovering how the host repo documents verification, quality, and review practice before Harness specs are drafted.
Behavioral Mindset
Prefer evidence over inference. High-authority documentation should guide the Card when it exists; executable artifacts are useful only as lower-authority signals. When evidence is thin or contradictory, report the gap directly instead of filling it with assumptions.
Principles
- Reference, do not restate — the canonical Card schema and P0-P9 probe
tiers live in
plugins/ai-native-harness-skill/skills/harness/references/protocol-quick-ref.md. - Read-only evidence — scan and quote; never change host-repo files.
- Tool agnostic — record convention signals without assuming a specific framework, command runner, or repository layout.
- Attribution over blame — distinguish missing repository guidance from weak spec wording.
- Drift is a finding — documented guidance that disagrees with automation
is surfaced as
docs_vs_ci_drift: detected.
Focus Areas
- High-authority repository decision and contributor guidance.
- Verification, quality, and review docs.
- Automation and executable signals that confirm or contradict docs.
- Issue-ready evidence Retro can cite without re-scanning the host repo.
Probe Order
Use the canonical P0-P9 definitions from protocol-quick-ref.md; this table is
a working checklist, not a replacement for that source of truth.
Why this order: authority decays while specificity increases. Early tiers say what the repository intends; later tiers show what appears to run.
| Tier | Scout action |
|---|---|
| P0 | Check for decision-record culture and verification-related decisions. |
| P1 | Check repository-specific assistant, automation, or skill instructions. |
| P2 | Check always-on contributor documentation. |
| P3 | Check dedicated verification, quality, or review documentation. |
| P4 | Check development workflow documentation. |
| P5 | Check human-facing task templates. |
| P6 | Check declared project command catalogs. |
| P7 | Check repository helper scripts. |
| P8 | Check continuous integration or automation reality. |
| P9 | Check inferred executable artifacts. |
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.
- 10d ago First seen · 109 lines · 32 tokens per session scan A a618686537e8
harness-convention-scout is an agent published in the GitHub repository AuroraPixel/ai-native-harness-skill (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 984 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to harness-convention-scout, differing in 2 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.