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 commands/zkwasm/concord-plugin/reportgit clone --depth 1 https://github.com/zkwasm/concord-pluginWhat 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 | $0.00017 | $0.00443 |
| Opus 5 | $0.00009 | $0.00221 |
| Sonnet 5 | $0.00003 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
report scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Set up a report room — a channel where you report work progress to a human who watches from the Concord dashboard and gets pinged when you're blocked or need a decision.
Steps
-
Authorize (one-time per machine). Call
concord_authorize(pass aclient_namelike"claude-code@$(hostname)").- The first call returns an
approve_url+user_code. Show both to the user and ask them to open the URL and click Approve. - Then call
concord_authorizeagain to finish. If it returnsstill_pending, the user hasn't approved yet — wait a moment and call it again. Repeat until it returnsauthorized. (If they already authorized on this machine, it returnsalready_authorized— skip to step 2.)
- The first call returns an
-
Create the report room. Call
concord_reportwith a short, human-meaningfulnamedescribing the task (e.g."Auth module refactor") and asender(your role). This creates a 📊 room owned by the user and binds this directory to it. -
Report as you work. Do your real task. Post concise updates with
concord_send, settinglevel:milestone— a step completed.blocked— you're stuck and can't proceed (pings the user).needs_decision— you need the user to choose; state the options (pings the user).done— finished.- omit
level(defaults toinfo) for routine notes.
-
Read replies. Between updates,
concord_pollfor the user's replies (e.g. a decision you asked for). They may be away — keep working and keep polling; an empty poll is not "done".
Use blocked/needs_decision sparingly and make each one actionable — they interrupt the human.
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.
- 2d ago First seen · 25 lines · 17 tokens per session scan A 02342be51cf2
report is a command published in the GitHub repository zkwasm/concord-plugin (2 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 443 once invoked, about $0.0001 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 commands, from other repositories
seo-drift
Compare two SEO snapshots (GSC / GSC AI Performance / rank tracker / AEO probe) and surface top movers per metric with auto-classification — growth / decline / reshuffle / stable / new / lost.
brand-setup
Configure a new brand profile with colors, fonts, logo, visual style, platforms, and compliance rules.
save
Save this conversation as a new or existing reusable context.
screens
Structures product UX screen design — inventory, flow, states, and reusable briefs for external design tools — without generating pixels or UI code.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
index
Command "index" from MadaraUchiha-314/the-loop, covering commands, the control plane, daemon commands, repo-scoped commands and maintenance.