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 Edge-City/agentvillage --skill index-networkgit clone --depth 1 https://github.com/Edge-City/agentvillageWrote 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/edge-city/agentvillage/index-network)<a href="https://agentmods.dev/skills/edge-city/agentvillage/index-network"><img src="https://agentmods.dev/badge/skills/edge-city/agentvillage/index-network/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/edge-city/agentvillage/index-network"><img src="https://agentmods.dev/badge/skills/edge-city/agentvillage/index-network.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 | $0.00054 | $0.00532 |
| Opus 5.5 | $0.00022 | $0.00213 |
| Sonnet 5.5 | $0.00011 | $0.00106 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
index-network 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 13d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Index Network — Edge City India
Edge's bundle for surfacing opportunities through Edge City India's Index Network integration. The Index Network MCP (server index) is the tool surface; this skill carries the Edge-flavored procedural knowledge for using it.
When to read each file
- Any non-trivial tool call → tools.md. MCP tool families, entity model, capturing new signal from conversation, output translation rules; at its end, the sections
AGENTS.mdpoints to: Cron schedule, URL preservation, Channel formatting, What the app knows about them, Backend notes. - Composing user-facing opportunity renderings → exemplars.md. Canonical morning-digest voice samples.
Read get_my_profile only to use the profile that already exists. Call update_my_profile only when they explicitly correct a field. A new want and a question about who is waiting both follow tools.md. The welcome in AGENTS.md is a separate first-message greeting. Do not send it again from here.
For a live private-chat reply about someone you recommended or an evening
meeting question, load rolodex. Check that person's current mark before
describing it; an accepted introduction is not proof they met. Let the owner
reflect, then offer the optional installed gold-stars mini-app (or its website)
if they want to thank someone. Recording an Index outcome, marking a Rolodex
meeting and sending a star are separate actions. Scheduled jobs still follow
their exact prompt and script output.
Handoff
The MCP server's own instructions carry the protocol-level rules (voice, vocabulary, entity model, output translation). Tool descriptions are authoritative; read them before calling. This skill adds only Edge City India-specific framing on top — never duplicate the MCP's behavioural guidance here.
When this shared skill says to reply silently or use a no-reply marker, use the marker for the host you are running in: Hermes → [SILENT]; OpenClaw → NO_REPLY; Claude Code → produce no user-facing text if the host supports a silent turn, otherwise stop without commentary.
What ships with it
60 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.
- exemplars.md 5.6 KB
- prompts/ask-questions.md 3.7 KB
- prompts/brief.md 6.0 KB
- prompts/memory-signals.md 8.1 KB
- prompts/negotiation-summary.md 4.1 KB
- prompts/opportunity-drop.md 3.8 KB
- prompts/pending-alert.md 2.9 KB
- scripts/approvals-waiting.ts 3.3 KB runs code
- scripts/ask-questions.ts 6.9 KB runs code
- scripts/build-daily-brief-context.ts 59 KB runs code
- scripts/context-tags.ts 17 KB runs code
- scripts/delivery-state.ts 14 KB runs code
- scripts/drop-opportunity.ts 6.2 KB runs code
- scripts/hermes-cli.ts 3.2 KB runs code
- scripts/index-mcp.ts 21 KB runs code
- scripts/job-settings.ts 32 KB runs code
- scripts/match-evidence.ts 7.8 KB runs code
- scripts/memory_signal_gate.py 66 KB runs code
- scripts/message-labels.ts 8.9 KB runs code
- scripts/outcome-ask.ts 19 KB runs code
- scripts/pause-job.ts 29 KB runs code
- scripts/pending-alert.ts 18 KB runs code
- scripts/proactive-text.ts 44 KB runs code
- scripts/proactive.ts 75 KB runs code
- scripts/question-guard.ts 21 KB runs code
- scripts/question-vocab.ts 5.4 KB runs code
- scripts/rating-cards.ts 19 KB runs code
- scripts/send-daily-brief.ts 8.3 KB runs code
- scripts/shims/agentvillage_proactive.sh 2.9 KB runs code
- scripts/stage-daily-brief.ts 12 KB runs code
- scripts/state-file.ts 811 B runs code
- scripts/state-lock.ts 8.1 KB runs code
- scripts/summarize-negotiations.ts 19 KB runs code
- scripts/tests/ask-questions.test.ts 13 KB runs code
- scripts/tests/build-daily-brief-context.test.ts 36 KB runs code
- scripts/tests/context-marks-corpus.ts 10.0 KB runs code
- scripts/tests/context-marks.test.ts 22 KB runs code
- scripts/tests/context-private-prompt.test.ts 3.7 KB runs code
- scripts/tests/context-private-skip.test.ts 11 KB runs code
- scripts/tests/context-tags.test.ts 24 KB runs code
- scripts/tests/delivery-cooldown.test.ts 34 KB runs code
- scripts/tests/delivery-paths.ts 7.6 KB runs code
- scripts/tests/delivery-schedule.test.ts 4.7 KB runs code
- scripts/tests/delivery-state.test.ts 12 KB runs code
- scripts/tests/digest-format.test.ts 2.2 KB runs code
- scripts/tests/digest-interests.test.ts 17 KB runs code
- scripts/tests/drop-opportunity.test.ts 9.4 KB runs code
- scripts/tests/fixtures/context-marks-golden.json 9.8 KB
- scripts/tests/fixtures/croniter_fixture.py 3.2 KB runs code
- scripts/tests/fixtures/croniter-6.0.0.json 305 KB
- scripts/tests/fixtures/croniter-fixture-input.ts 4.4 KB runs code
- scripts/tests/fixtures/index-create-direct.json 3.8 KB
- scripts/tests/fixtures/index-mcp-2026-07-28.json 9.7 KB
- scripts/tests/fixtures/index-origin-plugin.json 7.7 KB
- scripts/tests/fixtures/index-prepare-row153.json 8.5 KB
- scripts/tests/fixtures/lock-wait-child.ts 2.2 KB runs code
- scripts/tests/fixtures/outcome-stage-v1-origin-main.json 4.0 KB
- scripts/tests/fixtures/proactive-deadline-child.ts 1.1 KB runs code
- scripts/tests/fixtures/rc13-decision.ts 2.5 KB runs code
- scripts/tests/fixtures/welcome-texts.json 9.5 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.
- 13d ago Changed · +1 lines a67e5bae8581
- 15d ago Changed · +7 lines a84f95f2332b
- 19d ago Changed b51ca6b9a700
- 24d ago Changed · -1 tokens per session 14f97281018e
- 26d ago Changed · -2 tokens per session 6a053156e7fd
- 1mo ago First seen · 27 lines · 57 tokens per session scan A 6895dd1d3a26
index-network is a skill published in the GitHub repository Edge-City/agentvillage (21 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 532 once invoked, about $0.0002 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
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…