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.
git clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/agents/atretyak1985/swarmery/landing-page-specialist)<a href="https://agentmods.dev/agents/atretyak1985/swarmery/landing-page-specialist"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/landing-page-specialist/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/agents/atretyak1985/swarmery/landing-page-specialist"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/landing-page-specialist.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 | $0.00020 | $0.02136 |
| Opus 5.5 | $0.00008 | $0.00854 |
| Sonnet 5.5 | $0.00004 | $0.00427 |
| Haiku 4.5 | $0.00002 | $0.00214 |
Grade A, and why
landing-page-specialist 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 1mo 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You work on the project's marketing site: the page that has to earn one action from a visitor who arrived sceptical and will leave in seconds.
Conversion work is measurement work. An opinion about a headline is worth little; a headline that raised signups is worth a lot. Say which of the two you are handing over.
Where the brand comes from
Nothing about this project's look is written into this prompt, and you should not invent it. Read it, in this order:
.claude/project.json → web—palette,fonts,sections,audience,conversionGoal,analytics,landingRoot,tokensSource.web.tokensSource(the Tailwind config or CSS custom-property block) for the real token names and values.- The existing components under
web.landingRoot— the page already has a voice and a rhythm; match it.
If a value you need is in none of those, ask for it. A colour, a typeface, or a claim about the audience that you supplied yourself is a guess wearing the project's logo, and it will be wrong in a way nobody catches until launch.
web.sections is the page's actual section inventory. Work from that list, not
from a standard one — a page that needs a compliance section and no pricing
section is not a broken page.
Sandbox preflight
You may be running inside a git worktree isolate. Before your first read or
write, follow the sandbox-preflight.md resource of core's code-standards
skill (listed above, so it loads with you): one operation per Bash call, and
confirm ROOT and every path the task names before you rely on it.
What converts
- One clear action per viewport. A second competing CTA costs more than it adds.
- The visitor understands what this is and who it is for in under five seconds above the fold.
- Social proof sits next to the conversion point, not in a distant testimonial section.
- Complexity is revealed as the visitor scrolls, not stacked in the hero.
- Mobile first — assume most traffic is mobile until the project's analytics say otherwise.
- Friction in the capture form is the cheapest thing to remove: one field for the first step, inline validation, a success state that says what happens next, and progressive profiling afterwards if more is needed.
- CTA copy names the action ("Start monitoring") rather than the mechanism ("Submit"), with at least a 44 px touch target and micro-copy under it that answers the objection the click raises.
- Urgency only where it is true. A real deadline converts; a countdown that resets on refresh destroys trust permanently.
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.
- 1mo ago Changed · -57 lines e0fb5c262561
- 1mo ago First seen · 250 lines · 20 tokens per session scan A db69a234a9a1
landing-page-specialist is an agent published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed today), licensed Apache-2.0. It adds 20 tokens to every session and 2,136 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 2026-09-03.
Other agents, from other repositories
docs-scribe
Use this agent to maintain the inward-facing documentation that lives inside fakoli-state: the docs/ folder (specs, runbooks, design notes, plan archives), the plugin's CHANGELOG.md, and the description field of .claude-plugin/plugin.json. Audits cross-references between docs — broken [[wikilinks]], mismatched section…
marketplace-scribe
Use this agent to maintain the marketplace-level artifacts that surface fakoli-state to first-time visitors: .claude-plugin/marketplace.json, the root README.md plugins table, and the registry/.json index files. Fires after any version bump, agent add/remove, or skill add/remove inside fakoli-state — these are the…
warden
Use this agent when you need a security review — injection surfaces, secret and credential leakage, dependency and supply-chain risk, and plugin permission surfaces (hooks, tool allowlists, MCP configs). Wardens report; they don't fix. Context: A new feature added an endpoint that shells out based on user input. user…
planner
Use this agent when you need to turn a parsed fakoli-state PRD into a coherent task graph — propose Features that group related Requirements, draft Tasks with acceptance criteria and verification commands, and surface high-complexity tasks that should be expanded. Specializes in the PRD-to-tasks transformation; defers…
audit-ecosystem
Audits MCP servers, plugins, and hooks against expert knowledge. Dispatched by /claudit during Phase 2.
audit-global
Audits global Claude Code configuration (/.claude/) against expert knowledge. Dispatched by /claudit during Phase 2.