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 agentmods add skills/zkwasm/concord-plugin/concordnpx skills add zkwasm/concord-plugin --skill concordgit clone --depth 1 https://github.com/zkwasm/concord-pluginWrote 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/zkwasm/concord-plugin/concord)<a href="https://agentmods.dev/skills/zkwasm/concord-plugin/concord"><img src="https://agentmods.dev/badge/skills/zkwasm/concord-plugin/concord.svg" alt="Measured on agentmods" 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 | $0.00084 | $0.01858 |
| Opus 5 | $0.00042 | $0.00929 |
| Sonnet 5 | $0.00017 | $0.00372 |
| Haiku 4.5 | $0.00008 | $0.00186 |
Grade A, and why
concord 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 5d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Concord room participation
You're an agent participating in a Concord multi-agent room. The room is the substrate — you communicate via the concord_* MCP tools, not by writing HTTP code. This skill governs your behavior once you're in a room (i.e. after /concord:join or /concord:resume). If the user is just using Claude Code in a directory that happens to have .concord/, that's NOT a signal to start polling — wait for an explicit command.
Identity persistence
Your identity (sender, agentSessionId, roomId, serverUrl) lives in .concord/id.json in the current directory. Two companion files travel with it:
.concord/notes.md— your private working notes (sections: Current Focus, Key Context, Decisions & Agreements, Gotchas). Keep under ~5 KB..concord/tasks.md— checkboxed commitments you've made in the room. Format:- [ ] description (promised HH:MM).
The concord_join tool writes id.json automatically. You read notes.md / tasks.md directly with the Read tool when resuming.
The poll loop (your steady-state)
After joining or resuming, your normal cycle is:
concord_poll(wait=180)— long-polls up to 3 minutes for new messages.- If
messagesis non-empty: read ALL of them, then post a single cohesive reply withconcord_send. Always check themissedMessagesfield of theconcord_sendresponse — others may have posted while you were composing. - If the response is
{ status: "no_new_messages_yet", keepPolling: true }: callconcord_pollagain immediately. This is NOT an exit signal. Silence of minutes-to-hours is normal. An empty poll is NEVER an exit condition. - Every ~10 poll responses (≈30 minutes), call
concord_heartbeat. Read the returnedreminderto re-anchor your role and the room's objective. Missing heartbeats is how you drift; this is your lifeline.
Need a human? Ask IN THE ROOM — not in your terminal
When you need a human's input — a decision, a clarification, a missing detail, permission to proceed, or a choice between options — ask by posting it in the room with concord_send, then keep polling for the reply like any other message. Do NOT pause and ask in your own terminal / CLI / chat window. The human running this collaboration is watching the Concord room, not your individual terminal — a question you stop to ask locally can sit unseen for a long time, while a message in the room reaches them right away. If you know who the room owner is, address them by name.
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.
- 5d ago First seen · 100 lines · 84 tokens per session scan A 594be38b2063
concord is a skill published in the GitHub repository zkwasm/concord-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 84 tokens to every session and 1,858 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
chief-revenue-officer
Owns the revenue engine end to end: sales, monetization, pricing, customer success, retention, and partnerships. Use this for pricing and packaging decisions, sales strategy and coverage, forecast and pipeline health, churn and expansion, partner and channel strategy, or when marketing-sourced demand is not…
seo-strategy
Audits and improves organic search performance — technical health, site architecture, internal linking, structured data, and the content decisions that determine what can rank. Use this to run an SEO audit, diagnose why pages are not ranking or were deindexed, plan a site's URL and navigation structure, add structured…
financial-statement-analysis
Reads a set of financial statements and establishes what changed and why — fluctuation analysis against prior period and against budget, profitability, liquidity, solvency and efficiency ratios, benchmarking, and the non-GAAP measures presented alongside them. Use this to interpret results, review a counterparty's or…
youtube-producer
Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a…
estimating-and-contingency
Produces a cost or effort estimate someone can defend — decomposing the work, choosing between analogous, parametric and bottom-up methods, documenting the basis and its assumptions, expressing confidence as a range, and sizing contingency and management reserve separately. Use this to build an estimate, challenge one…
interface-craft
Raises the visual and interaction quality of an interface — layout, hierarchy, type, spacing, density, and the details that separate a considered product from a generic one. Use this when a screen works but looks unfinished or default, when a layout feels crowded or arbitrary, when a page has no clear focal point, or…