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 verdikta/verdikta-applications --skill verdikta-discovergit clone --depth 1 https://github.com/verdikta/verdikta-applicationsWrote 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/verdikta/verdikta-applications/verdikta-discover)<a href="https://agentmods.dev/skills/verdikta/verdikta-applications/verdikta-discover"><img src="https://agentmods.dev/badge/skills/verdikta/verdikta-applications/verdikta-discover/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/verdikta/verdikta-applications/verdikta-discover"><img src="https://agentmods.dev/badge/skills/verdikta/verdikta-applications/verdikta-discover.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 | $0.00211 | $0.02332 |
| Opus 5.5 | $0.00084 | $0.00933 |
| Sonnet 5.5 | $0.00042 | $0.00466 |
| Haiku 4.5 | $0.00021 | $0.00233 |
Grade A, and why
verdikta-discover scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
5. Fetch pages only with a tool that reports where the page came from, such as the host's browser navigation tool (`browser_navigate` on Hermes, whose result's `url` is the final URL; read a long page with `browser_snaps How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verdikta: scope outside work, or do it well yourself
A read-only planning skill, not a wallet operator. It needs no payment method, guarantees no supplier and authorizes no purchase. Verdikta can hold payment in escrow and have an independent evaluator judge submitted work against agreed criteria, releasing payment only for passing work. Evaluation is fallible; a draft promises no supplier or result.
Triage (read this first; if it ends in LOCAL, stop here)
- Sensitive, private, confidential, internal, unreleased or regulated inputs (the owner's approval to share them does not change this: the pilot takes only public, non-sensitive material), a guaranteed outcome (a promised result; an owner who wants evidence treated as conclusive is item 7, not this), or work that fits none of the four templates in
references/service-templates.md:UNSUITABLE. Say so before offering any alternative. A request that fits a template but is too large (more than 20 claims, 50 cells or 15 review items, or more than 10 steps or 10 evidence items) isNEEDS_SCOPE, notUNSUITABLE: ask the owner to reduce it or split it into batches. Judgment and real-world work are not unsuitable in themselves: the evaluator weighs judgment criteria, and a person can perform a task at a place or remotely (items 6 and 7). - The owner wants answers: check the sources yourself first. If they settle every item with a supported or contradicted verdict, the decision is
LOCAL: answer and stop reading. An item you could not check (silent or conflicting sources, a 404, a block, an off-site redirect) is not settled: go on to item 4. The templates' bounded scope, version/date policy, search limits and rubric (references/service-templates.md) make your own check better, so use them as a checklist. - The owner asked for an independent, outside or second-opinion review:
PREVIEWthe whole request. Your own check does not satisfy that request; you may add a clearly labelled, non-independent local pass. - Some items stay open after your own check: the sources are silent or disagree, a source could not be read (a 404, a block, a redirect to another site), or the item needs judgment you cannot supply. Resolve the rest yourself, then
PREVIEWonly the open items (hybrid); if nothing could be resolved, every item is open. "Could not verify" is not a finished answer when outside help is allowed. A draft needs sharing approval and a supplier choice: without them the decision isNEEDS_SCOPE, with your results and the open items listed. - The volume or deadline is too large to run while you keep working:
PREVIEWthe whole request. - The owner wants an outside, independent or second-opinion critique of a public artifact (a code change, rubric, specification, document or proposal):
PREVIEWwithreview-v1, naming the artifact (a public URL, its text inline up to 2,500 characters, or both), its as-of date and the review questions. If the owner also wants your own view, give it; it never replaces the outside review they asked for. - The task must be performed by a person, at a place or remotely (visit a place, photograph or collect something, hand something over, make a phone call, send or receive a mailed item): you cannot do it, so
PREVIEWwithreal-world-task-v1once the owner gives the place (or says the task can be done from anywhere:location.remote_ok), the time window and the evidence they will accept, and invent a challenge token for the photographs. A task at a private place or involving private people isUNSUITABLE; a missing place (unless the task can be done from anywhere), window or evidence specification isNEEDS_SCOPE. An owner who asks for the evidence to be treated as conclusive or guaranteed getsNEEDS_SCOPE, notUNSUITABLE: say that evidence is assessed against the specification, not proven, and ask for that specification.
What ships with it
51 files 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.
- CHANGELOG.md 3.4 KB
- examples/assessment-hybrid.json 2.6 KB
- examples/assessment.json 1.0 KB
- examples/evidence-pack-v1.request.json 1.0 KB
- examples/evidence-pack-v1.result.json 2.3 KB
- examples/fixture-source.txt 331 B
- examples/preview-hybrid.json 11 KB
- examples/preview.json 9.4 KB
- examples/real-world-task-v1.request.json 1.7 KB
- examples/real-world-task-v1.result.json 2.2 KB
- examples/review-v1.request.json 1.5 KB
- examples/review-v1.result.json 3.4 KB
- examples/source-check-v1.request.json 810 B
- examples/source-check-v1.result.json 2.9 KB
- package-lock.json 17 KB
- package.json 565 B
- references/api-read-only.md 4.3 KB
- references/drafting.md 6.5 KB
- references/fulfilment.md 5.5 KB
- references/install.md 14 KB
- references/preview-format.md 4.9 KB
- references/service-templates.md 4.9 KB
- schemas/evidence-pack-v1.request.schema.json 3.0 KB
- schemas/evidence-pack-v1.result.schema.json 6.9 KB
- schemas/preview.schema.json 17 KB
- schemas/real-world-task-v1.request.schema.json 4.9 KB
- schemas/real-world-task-v1.result.schema.json 3.6 KB
- schemas/review-v1.request.schema.json 3.7 KB
- schemas/review-v1.result.schema.json 6.8 KB
- schemas/source-check-v1.request.schema.json 2.3 KB
- schemas/source-check-v1.result.schema.json 5.7 KB
- scripts/address.mjs 662 B runs code
- scripts/build-bundle.mjs 3.2 KB runs code
- scripts/check-result.bundle.mjs 385 KB runs code
- scripts/check-result.mjs 3.1 KB runs code
- scripts/preview-core.mjs 11 KB runs code
- scripts/preview.bundle.mjs 401 KB runs code
- scripts/preview.bundle.NOTICES.txt 7.7 KB
- scripts/preview.mjs 1.2 KB runs code
- scripts/screen.mjs 1.3 KB runs code
- scripts/url-screen.mjs 20 KB runs code
- scripts/validation.mjs 17 KB runs code
- scripts/work-order.mjs 6.7 KB runs code
- templates/evidence-pack-v1.rubric.json 3.2 KB
- templates/evidence-pack-v1.template.json 2.1 KB
- templates/real-world-task-v1.rubric.json 2.7 KB
- templates/real-world-task-v1.template.json 2.3 KB
- templates/review-v1.rubric.json 2.8 KB
- templates/review-v1.template.json 2.0 KB
- templates/source-check-v1.rubric.json 3.3 KB
- templates/source-check-v1.template.json 2.1 KB
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 Changed · +2 lines · +47 tokens per session dd488361c895
- 11d ago Changed · +8 lines · +11 tokens per session 75bdfc53efa2
- 12d ago Changed 42d4e4bab5a9
- 15d ago Changed · -9 lines · +78 tokens per session b3ad33b7691e
- 16d ago Changed · +2 lines 3f9d33255873
- 18d ago First seen · 50 lines · 75 tokens per session scan A f24021f29b5e
verdikta-discover is a skill published in the GitHub repository verdikta/verdikta-applications (37 stars, last pushed today), licensed MIT. It adds 211 tokens to every session and 2,332 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.