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 cristianmoroaica/bountyverdict --skill route-github-agent-checksgit clone --depth 1 https://github.com/cristianmoroaica/bountyverdictWrote 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/cristianmoroaica/bountyverdict/route-github-agent-checks)<a href="https://agentmods.dev/skills/cristianmoroaica/bountyverdict/route-github-agent-checks"><img src="https://agentmods.dev/badge/skills/cristianmoroaica/bountyverdict/route-github-agent-checks/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/cristianmoroaica/bountyverdict/route-github-agent-checks"><img src="https://agentmods.dev/badge/skills/cristianmoroaica/bountyverdict/route-github-agent-checks.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 | $0.00060 | $0.01136 |
| Opus 5 | $0.00030 | $0.00568 |
| Sonnet 5 | $0.00012 | $0.00227 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
route-github-agent-checks 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Route Agent Decision Checks
Choose exactly one bounded live check, validate its unpaid x402 challenge, and use the typed result as a decision gate. Do not buy a broad bundle when one endpoint answers the task.
Select the check
| Need | Product | Method and path | Maximum | Operating skill |
|---|---|---|---|---|
| Assess one public bounty issue | BountyVerdict | POST /api/bounty-preflight |
50,000 atomic USDC | preflight-github-bounties |
| Rank 2–10 public bounty issues | BountyVerdict Portfolio | POST /api/portfolio |
400,000 atomic USDC | preflight-github-bounties |
| Audit repository coding-agent instructions | HarnessVerdict | POST /api/repository-agent-instructions-audit |
30,000 atomic USDC | audit-agent-harness |
| Audit one public skill before installation | SkillVerdict | GET /api/skill |
60,000 atomic USDC | preflight-agent-skills |
| Diagnose one public GitHub Actions run | RunVerdict | POST /api/github-actions-run-diagnosis |
40,000 atomic USDC | diagnose-github-actions |
| Decide whether one completed failed run merits a retry | FlakeVerdict | POST /api/github-actions-flake-retry-gate |
70,000 atomic USDC | classify-github-flakes |
| Gate a tools/list catalog change | MCPDriftVerdict | POST /api/mcp-drift |
20,000 atomic USDC | check-mcp-tool-drift |
Use RunVerdict when the root cause or next repair action is unknown. Use FlakeVerdict only for the narrower retry-versus-investigate decision. Use MCPDriftVerdict only with complete inline 2025-11-25 protocol snapshots; never use it to connect to or invoke a catalog-serving endpoint. If no row fits, do not purchase; find a more relevant service.
Resolve the live contract
- Read
https://cristianmoroaica.github.io/bountyverdict/agent-manifest.json. - Require
statusto equalactive,production_apito equal the exact originhttps://bountyverdict-agent-production.mimirslab.workers.dev, and the selected product entry to match the table above. - Require that product's
skill_urlto equalhttps://cristianmoroaica.github.io/bountyverdict/skills/<OPERATING-SKILL>/SKILL.md, using the operating-skill name from the table. Read it and follow its product-specific input validation, challenge validation, result interpretation, and retry rules. - Inspect the product's free
sampleand<production_api>/openapi.jsonbefore paying.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 55 lines · 60 tokens per session scan A dbf1b4052768
route-github-agent-checks is a skill published in the GitHub repository cristianmoroaica/bountyverdict (0 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,136 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 skills, from other repositories
ios-app-store-submit
Build, sign, and submit a Flutter/iOS app to the App Store Connect — covers Xcode archive/export, code signing (including headless-Mac keychain workarounds), the asc CLI for App Store Connect metadata automation, screenshot handoff, and final review submission. Use when asked to build and upload an iOS app, set up App…
pr-reviewer
A pull-request review workflow for checking team-specific coding style, naming, and code structure. A pull request is a proposed change to a codebase that teammates inspect before merging.
task
Create one or more tasks via wade task create — for a single bug/feature OR a full plan/PRD breakdown. This is the STANDALONE task-creation workflow, used whenever the user directly asks to create a task/issue outside a wade plan session. Assesses scope, proposes a single- or multi-issue breakdown with reasoning, gets…
knowledge
Instructions for contextual knowledge retrieval, tagging, search, and rating. Referenced by fixed planning, implementation, and review workflow bundles.
planning
Analyze a software change and turn it into evidence-based, cohesive implementation tasks.
code-review
Review a code change for correctness, security, maintainability, tests, and scope alignment.