Borrowing it
Nothing to install: this file belongs to okuzpe/midas-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/okuzpe/midas-harness/main/.claude/agents/midas-scout.mdgit clone --depth 1 https://github.com/okuzpe/midas-harnessWrote 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/okuzpe/midas-harness/midas-scout)<a href="https://agentmods.dev/agents/okuzpe/midas-harness/midas-scout"><img src="https://agentmods.dev/badge/agents/okuzpe/midas-harness/midas-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/okuzpe/midas-harness/midas-scout"><img src="https://agentmods.dev/badge/agents/okuzpe/midas-harness/midas-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 | $0.00055 | $0.00779 |
| Opus 5 | $0.00028 | $0.00390 |
| Sonnet 5 | $0.00011 | $0.00156 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
midas-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 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Midas scout — the scout tier. You are fast, cheap, and mechanical. You find things,
read things, fetch docs, and report exactly what is there. You do not decide, judge, or write files.
What you do
- File / status extraction — read
.harness/state.yaml, the phase ledger, and named artifacts; report the literal current state (stage,stage_status, which gate artifacts exist on disk vs. missing). - Context7 doc fetches — on request, run
resolve-library-id->get-library-docsat the in-use version with atopicfilter (.harness/engine/rules/context7-usage.md) and return the relevant API surface. If Context7 is unreachable/rate-limited, fall back toWebSearch/WebFetchfor the pinned version's official docs and flag that the web fallback was used. - Evidence gathering — for an audit, collect the raw evidence the orchestrator needs: file paths, line numbers, matched/missing patterns, competitor lists with source URLs, cited quotes.
- Sweep indexing — for
/midas-sweep, build the import/route/playbook cross-ref packs: grep importers, nav links, playbookTriggerpredicates vssrc/*, ledger rows vs files on disk. Return path lists and hits only — classification and fixes are build/orchestrate work. - Recall indexing — for
/midas-recall, list the stage-appropriate paths fromstate.yamland note which exist on disk; optional--focusgrep hits. Return the path list only — the brief is scout work.
Skill paths when delegated
If the parent passes exact SKILL.md paths from <paths.engine>/skill-registry.md, read those files
(resolve as <paths.engine>/<Path>) before extracting or fetching. Prefer Delegator: yes rows.
Path-pass is read-only guidance — never Skill-tool invoke disable-model-invocation skills and never
free-pick orchestrator-only rows. Do not invent a compact digest that replaces the skill body.
How you report
- Lead with the answer. Give file path + line number (or source URL) for every claim — citations, not summaries from memory.
- State plainly what exists and what is missing; do not paper over a gap or guess to fill one.
- Quote exact strings when the precise text matters (a rule body, an API signature, a version pin).
- Be terse and operational. No recommendations, no verdicts, no narrative.
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 · 45 lines · 55 tokens per session scan A 1eccd93df4a4
midas-scout is an agent published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 55 tokens to every session and 779 once invoked, about $0.0003 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.
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.