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 agentmods add skills/mimirs402/bountyverdict/classify-github-flakesnpx skills add Mimirs402/bountyverdict --skill classify-github-flakesgit clone --depth 1 https://github.com/Mimirs402/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/mimirs402/bountyverdict/classify-github-flakes)<a href="https://agentmods.dev/skills/mimirs402/bountyverdict/classify-github-flakes"><img src="https://agentmods.dev/badge/skills/mimirs402/bountyverdict/classify-github-flakes.svg" alt="Measured on agentmods" 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 | $0.00074 | $0.01002 |
| Opus 5 | $0.00037 | $0.00501 |
| Sonnet 5 | $0.00015 | $0.00200 |
| Haiku 4.5 | $0.00007 | $0.00100 |
Grade A, and why
classify-github-flakes 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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- classify-github-flakes — 98% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Classify GitHub Flakes
Use FlakeVerdict as a read-only retry gate. It inspects public GitHub Actions evidence and never reruns CI or executes repository code.
Resolve the exact service
- Read
https://mimirs402.github.io/bountyverdict/agent-manifest.jsonfor availability, then require itsproduction_apito equal the exact originhttps://bountyverdict-agent-production.mimirslab.workers.dev. - Inspect the free sample at that origin and its
/openapi.jsondocument. - Accept only a canonical public run URL shaped like
https://github.com/OWNER/REPO/actions/runs/RUN_IDwith no credentials, query, fragment, job suffix, or alternate host. - Add
attemptonly when selecting a known positive run-attempt integer. Omit it to inspect the latest available attempt.
Construct the exact resource as:
POST https://bountyverdict-agent-production.mimirslab.workers.dev/api/github-actions-flake-retry-gate
Content-Type: application/json
{"run_url":"<CANONICAL_RUN_URL>","attempt":<OPTIONAL_POSITIVE_INTEGER>}
Do not send credentials, private-repository URLs, pasted logs, or arbitrary text.
Verify before paying
Make the exact request without payment first. Require all of these before authorizing payment:
- HTTP
402using x402 v2 and theexactscheme; - exact service name
FlakeVerdictand Bazaar methodPOSTwith a strict JSON body; - exact production origin and exact resource URL constructed above, with no query parameters;
- Base mainnet network
eip155:8453; - canonical Base USDC asset
0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913; - exact recipient
0x4aa55988fA032FBbB8DDEf496b0f194FEc62D614; - an amount no greater than
70000atomic units (0.07 USDC).
Bind the payment client to that exact origin, network, asset, recipient, service, method, resource, and 70,000-atomic cap. Standard x402 authorizes the resource URL rather than the POST body, so verify the advisory normalized-body SHA-256 and preserve the exact validated JSON on the signed retry. Reject any redirect, changed challenge, body change, additional payment option, or mismatch. Never reveal wallet secrets, seed phrases, API keys, private keys, or payment signatures. After a timeout or ambiguous response, reconcile the wallet and settlement state before considering another identical request; never pay blindly twice.
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.
- 3d ago First seen · 56 lines · 74 tokens per session scan A 86c67ed109f7
classify-github-flakes is a skill published in the GitHub repository Mimirs402/bountyverdict (1 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 1,002 once invoked, about $0.0004 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
use-vercel-action
Wire amondnet/vercel-action into a GitHub Actions workflow to deploy Vercel projects from CI. Use when the user asks to deploy to Vercel from GitHub Actions, add Vercel preview deploys, post a Vercel preview URL on a PR, configure prebuilt Vercel deployments, set up alias domains for previews, create a GitHub…
agents-shipgate
Run prominent Agents Shipgate flows when a change touches what an AI agent can do: shipgate check, agents-shipgate verify, or shipgate audit --host. Use after adding or modifying MCP servers or tools, tool/function definitions (@tool, @functiontool), OpenAPI specs that describe agent tools, agent prompts, permission…
agents-shipgate
Use when the user wants to run the prominent Agents Shipgate flows — shipgate check, agents-shipgate verify, or shipgate audit --host — for AI agent capability changes, PR release readiness, or coding-agent host grants.
github-workflow-automation
Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management.
github-actions-workflow
Scaffolds or audits a GitHub Actions CI/CD workflow for a project. Covers job structure, caching, secrets handling, concurrency groups, environment gates, and reusable workflows via workflowcall. Invoked when the user asks to set up CI, add a GitHub Actions workflow, improve pipeline performance, or share workflow…
astro-github-actions
Sets up GitHub Actions CI/CD workflows for Astro sites — astro check (TypeScript + content schema), ESLint, Prettier, build verification, Vitest testing, Lighthouse CI, link checking, npm audit, and automated deployment to GitHub Pages, Cloudflare Pages, Netlify, or Vercel. ALWAYS use this skill when a user wants to…