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 kangig94/coral --skill discussgit clone --depth 1 https://github.com/kangig94/coralWrote 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/kangig94/coral/discuss)<a href="https://agentmods.dev/skills/kangig94/coral/discuss"><img src="https://agentmods.dev/badge/skills/kangig94/coral/discuss/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/kangig94/coral/discuss"><img src="https://agentmods.dev/badge/skills/kangig94/coral/discuss.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 | $0.00016 | $0.00719 |
| Opus 5 | $0.00008 | $0.00360 |
| Sonnet 5 | $0.00003 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
discuss 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 9d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Moderated Multi-Agent Discussion
Start a backend-managed structured discussion with AI agents.
Pass --user to participate as a human observer.
Execution
-
If no topic is provided: gather it interactively, plus:
- participant count (2-8, default: 4)
- debate vs open discussion
- requested roles or perspectives
-
Analyze the topic and prepare persona inputs.
- Identify the professional domain and the main disagreement axes.
- If geographic or institutional origin matters, prepare
demographics: { origin_weights, outlier_ratio }. - Write a 1-2 sentence background brief per slot.
- Assign a distinct name culture per slot.
-
Generate persona seeds with:
coral-cli discuss seed --input-json -using the prepared{ controversy_axes, n, demographics?, seed }payload on stdin. -
Turn the seed output into personas.
- Use the seed positions, tone, and any
suggested_origin/is_outlierfields. - Reuse your normal persona-generation workflow if you have one.
- Keep agent names stable and tool-safe.
- Use the seed positions, tone, and any
-
Build the agent list and start the session.
- Required AI agents use
{ name, persona, provider?, model? }. - If
--user, add:{ name: 'user', persona: '# User — Human Participant\nHuman observer with real-time participation via /bid skill.', participation: 'observer' } - Start with:
coral-cli discuss start --input-json -for the full{ topic, agents, config? }payload. Includeconfig: { min_bid_delay_ms: 10000 }for--user; omitconfigotherwise. - Save the session from
Session started: <session_id>.
- Required AI agents use
-
If
--user, writeCORAL_PROJECT/discuss/active-user-session.jsonwith{ session_id }. This keeps/bidpointed at the active observer session. -
Monitor progress by polling:
coral-cli discuss watch --session "<session_id>"- First poll: omit
cursor. - Subsequent polls: pass the
Cursor: <n>value printed in the watch output:coral-cli discuss watch --session "<session_id>" --cursor <previous_cursor> - Use the watch summary to track session status, epoch, step, and cursor progression.
- First poll: omit
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.
- 9d ago First seen · 70 lines · 16 tokens per session scan A 1cf01d914c60
discuss is a skill published in the GitHub repository kangig94/coral (11 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 719 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
deployment
This skill should be used when shipping an app to production — setting up CI/CD, deploys, preview environments, error monitoring, environment separation, or rollback. Trigger phrases include "deploy this", "set up CI/CD", "GitHub Actions", "add error tracking", "set up Sentry", "monitor production", "staging…
api-design
This skill should be used when designing or building an API — endpoints, routes, request/response shapes, error formats, pagination, versioning, or deciding REST vs GraphQL. Trigger phrases include "design the API", "build an endpoint", "REST or GraphQL", "how should I structure my routes", "API error format"…
architecture-primer
This skill should be used when the user wants to design, plan, or decide the architecture of a system, app, or platform from scratch. Trigger phrases include "how do I structure this", "what architecture should I use", "how does this scale", "monolith or microservices", "what database", "what stack", "design the…
saas-router
This skill should be used FIRST whenever the user wants to create, build, design, ship, or prototype any digital product — a SaaS, web app, platform, MVP, landing page, sales page, dashboard, admin panel, backoffice, internal tool, API, database, auth, payments, or any user interface. Trigger phrases (English) include…
ui-design
This skill should be used when making visual design decisions, creating components, defining styles, colors, typography, spacing, or building any interface — including dashboards, admin panels, and web apps. Trigger phrases include "design the UI", "build a component", "pick colors", "create a design system", "make it…
auth
This skill should be used when adding authentication or authorization to an app or SaaS — login, signup, sessions, tokens, roles, permissions, multi-tenant access, SSO, or social login. Trigger phrases include "add login", "add auth", "sign in with Google", "protect this route", "user roles", "admin permissions", "JWT…