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/dimitrigeelen/agentic-engineering-framework/check-arcgit clone --depth 1 https://github.com/DimitriGeelen/agentic-engineering-frameworkWrote 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/commands/dimitrigeelen/agentic-engineering-framework/check-arc)<a href="https://agentmods.dev/commands/dimitrigeelen/agentic-engineering-framework/check-arc"><img src="https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/check-arc.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 | $0.00000 | $0.01571 |
| Opus 5 | $0.00000 | $0.00785 |
| Sonnet 5 | $0.00000 | $0.00314 |
| Haiku 4.5 | $0.00000 | $0.00157 |
Grade A, and why
check-arc 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 today.
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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/check-arc - Pending Chat-Arc DM Inbox (RECEIVE-side companion to /agent-handoff)
Surface pending agent-chat-arc DMs targeted at this agent. Read-side counterpart
to /agent-handoff. Walks dm:<self-fp>:* topics, computes unread counts via
termlink channel unread, renders a Slack-style summary.
Invocation:
/check-arc(no arguments) → Browse mode (read-only)./check-arc respond→ Respond mode (ack + reply). This is the formagent-send.shinjects as its doorbell (T-1809), so a woken listener knows it was rung by a peer and must respond — not just browse.
This skill has two modes:
- Browse mode (default, manual) — read-only. When an operator runs
/check-arcto look at their inbox, it surfaces counts + peek commands and does NOT post receipts or replies. The caller acks explicitly per topic. - Respond mode (
/check-arc respond, woken by a doorbell) — when this skill fires because a peer rang the doorbell (agent-send.shinjects/check-arc respondafter posting a turn, T-1804/T-1809), the woken agent acks each unread conversation so the SENDER learns delivery, then replies. Go straight to "Step 6 — Respond mode" below. The ack is delegated to the deterministicscripts/agent-respond.sh(T-1805) so the receipt is the exact shapeagent-send.shpolls for.
Argument contract: if the skill is invoked with the argument respond (i.e.
$ARGUMENTS contains respond), branch to Step 6 (Respond mode) after Steps 1–4
gather the unread set. Otherwise run Steps 1–5 (browse) and stop before Step 6.
Step 1: Resolve self identity fingerprint
Run:
termlink whoami --json
If the output's session.identity_fingerprint is populated, use it.
Otherwise fall back to discovering self-fp from any recent
agent-chat-arc post owned by this caller — but if neither path resolves,
stop and print:
check-arc: cannot resolve self identity_fingerprint.
Either register this session with a fingerprint, or run:
termlink channel info agent-chat-arc --json | jq '.senders'
to identify yourself manually.
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.
- today First seen · 176 lines · 0 tokens per session scan A 295bc74fae5f
check-arc is a command published in the GitHub repository DimitriGeelen/agentic-engineering-framework (13 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,571 tokens. 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 2026-09-04.
Other commands, from other repositories
list
List recent task executions across all agents.
pause
Pause one or more schedules to temporarily stop automated executions.
service-check
Request each agent to run a self-diagnostic to validate their runtime setup.
compatibility-audit
Audit all agents for Trinity compatibility by requesting self-diagnostics from each agent.
request-research
Ask the researcher to investigate a specific topic.
schedules
Quick overview of all schedules across the platform.