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 rolodexgit 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/rolodex)<a href="https://agentmods.dev/skills/edge-city/agentvillage/rolodex"><img src="https://agentmods.dev/badge/skills/edge-city/agentvillage/rolodex/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/rolodex"><img src="https://agentmods.dev/badge/skills/edge-city/agentvillage/rolodex.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 | $0.00115 | $0.02196 |
| Opus 5.5 | $0.00046 | $0.00878 |
| Sonnet 5.5 | $0.00023 | $0.00439 |
| Haiku 4.5 | $0.00012 | $0.00220 |
Grade C, and why
rolodex scanned grade C 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 11d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
Naman as met in your Rolodex; it already lists everyone in the village.” Never say you cannot add people or invent an add action. Under `mini_app_not_installed`, How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Village Rolodex
The Rolodex is Agent Village's directory of people in the village. It shows shared profiles, Telegram introductions and Skylight characters where available. The signed-in person can mark We met, undo it with Undo met, and send Gold Stars. These are separate actions: recording a meeting does not send a star.
When asked, give the useful link immediately: https://agents.edgecity.live/rolodex
The native operations below come with the optional Gold Stars mini-app.
If village answers mini_app_not_installed, it is not available on this agent
yet (or Gold Stars is not installed): acknowledge the interaction, offer the Rolodex link where they
can mark the meeting themselves, and never claim you updated a mark.
For who is X, that or any other failure means you go on to the edgeos directory
this turn (AGENTS.md order). Never call Rolodex or the directory unavailable from
earlier in the conversation: an earlier failure is stale, so call again now.
For “I met Naman”, call village with operation: "rolodex.search" and
query: "Naman". Use the returned attendee id. Prefix a returned /rolodex path with
https://agents.edgecity.live when sharing its link. If more than one person fits,
ask which one, using their shared role/organization to distinguish them. Never
choose the first result, guess an id, or infer a meeting from a match. Then
call rolodex.meeting with that attendeeId and met: true. A clear request
to undo uses met: false. Search again if the target is unclear.
“Add Naman to my Rolodex” (or put/save them in the Rolodex, contacts or people)
means the same as “I met Naman”: everyone in the village is already in the
Rolodex, and We met is its only mark. Follow the same search, disambiguation
and marking rules, call rolodex.meeting with met: true, then say “I've marked
Naman as met in your Rolodex; it already lists everyone in the village.” Never
say you cannot add people or invent an add action. Under mini_app_not_installed,
offer the Rolodex link where they can mark the meeting themselves.
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.
- 11d ago Changed · +8 lines · +12 tokens per session scan A → C 70b14177b6fb
- 12d ago Changed · +44 lines · +18 tokens per session 3cda675ecbf2
- 13d ago Changed · +7 lines · +20 tokens per session 20a75d048268
- 15d ago First seen · 92 lines · 65 tokens per session scan A 66c8924dba5f
rolodex is a skill published in the GitHub repository Edge-City/agentvillage (21 stars, last pushed today), licensed MIT. It adds 115 tokens to every session and 2,196 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-13.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.