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 plangit 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/plan)<a href="https://agentmods.dev/skills/kangig94/coral/plan"><img src="https://agentmods.dev/badge/skills/kangig94/coral/plan/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/plan"><img src="https://agentmods.dev/badge/skills/kangig94/coral/plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 13 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 15 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Rogue Agent · line 34 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00022 | $0.06196 |
| Opus 5.5 | $0.00009 | $0.02478 |
| Sonnet 5.5 | $0.00004 | $0.01239 |
| Haiku 4.5 | $0.00002 | $0.00620 |
Grade A, and why
plan 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 today.
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 — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning
Execute a multi-round planning session with architect/critic review.
Argument Routing
| Argument | Mode |
|---|---|
<prompt> |
Self-execute on current host (default) |
--delegate |
Add a review pass on <other-host> (see Review Phases for the mapping). On a host that is not itself a provider it replaces Phase 2 rather than adding to it, so the net is still one review phase. |
round=N |
Review rounds for every applicable phase (default 1). e.g. round=3 for deeper iteration. |
round=N,M,… |
Per-phase budget, one value per phase in order: Phase 1 gets N, Phase 2 gets M, and any further value adds that phase. A 0 skips its phase. Two or more values turn --delegate on. |
--no-handoff |
Internal: skip implementation prompt at step 5 (caller controls next step) |
Reviewers and the resolver always run in every review phase that dispatches — the round budget only sets how many times each phase iterates.
Parsing the round budget (round=… and --round=… are the same token):
round=N→ every applicable phase getsN. Does not affect--delegate, so on its own it is Phase 2 alone; with--delegateit is Phase 1 and Phase 2.round=N,M,…→ the i-th value is{maxRounds[i]}, for as many values as are written, and--delegateis on whether or not it was written. Phase 1 exists only under--delegate, so naming a budget per phase IS the request for those phases.- A value of
0skips its phase: that phase does not dispatch and reports as skipped.round=1,0is one delegated round and no local review;round=0,2is two local rounds and no delegation. - More than two values extends the review beyond Phase 2, alternating hosts: odd phases run on
<other-host>, even phases on<phase-2-provider>.round=1,1,3is one delegated round, one local round, then three more delegated rounds as Phase 3. - Absent →
1for every applicable phase. - Every value must be an integer ≥ 0. A negative value or a non-integer is a usage error: report it and stop. Do not clamp or fall back to the default. There is no cap on how many values may be given.
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.
- today Changed · +1 lines 511ef61a1cee
- 5d ago Changed 7e1670ec1b16
- 29d ago Changed · +16 lines b3c47e92df44
- 1mo ago Changed · +5 lines · +1 tokens per session 20b011c309dc
- 1mo ago First seen · 328 lines · 21 tokens per session scan A 0969d556bffc
plan is a skill published in the GitHub repository kangig94/coral (11 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 6,196 once invoked, about $0.0001 per session on Opus 5.5. 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
rls-audit
This skill should be used to audit Row-Level Security and database permissions on a Postgres backend exposed through an auto-generated API — Supabase, InsForge, or any Postgres + PostgREST setup. Trigger phrases (English) include "audit my RLS", "review my policies", "is my database exposed", "can users see each…
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, an integration, an AI feature, or any user interface.…
ai-features
This skill should be used when putting an LLM inside the product itself — a chatbot or support agent, AI-generated reports or summaries, classification, extraction, lead scoring, a WhatsApp or voice bot, or any feature where your code calls a model on behalf of your users. Trigger phrases (English) include "add AI to…