Borrowing it
Nothing to install: this file belongs to DimitriGeelen/agentic-engineering-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DimitriGeelen/agentic-engineering-framework/master/.claude/commands/pulse.mdgit 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/pulse)<a href="https://agentmods.dev/commands/dimitrigeelen/agentic-engineering-framework/pulse"><img src="https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/pulse/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/commands/dimitrigeelen/agentic-engineering-framework/pulse"><img src="https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/pulse.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 | $0.00000 | $0.01669 |
| Opus 5.5 | $0.00000 | $0.00668 |
| Sonnet 5.5 | $0.00000 | $0.00334 |
| Haiku 4.5 | $0.00000 | $0.00167 |
Grade A, and why
pulse 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 1mo 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pulse — single-shot conversation arc digest (T-1860 composition)
The "is the rail alive and what's the pulse?" verb. Composes /peers
(LIST) + /recent-chat (READ) into one unified situational view, so an
operator landing fresh can answer "what's happening on the arc right now?"
in one keystroke instead of three.
Read-only, no state mutation, no auth — pure parallel composition of existing wrappers.
This is the cold-start companion verb to the six-corner skill set
(T-1859). The corners stay specialized; /pulse is the integrator.
Invocation:
| Form | Action |
|---|---|
/pulse |
Default: LIVE peers + last 5 chat-arc posts, 24h window |
/pulse 10 |
Show 10 chat-arc posts instead of 5 |
/pulse 5 168 |
5 posts over a 7-day window |
/pulse --json |
Machine-readable envelope (merge of both wrappers' JSON) |
The skill never writes state. Always safe to invoke.
Step 1: Pre-flight
Run:
bash scripts/agent-listeners-fleet.sh --help >/dev/null 2>&1 && \
bash scripts/agent-chat-arc-recent.sh --help >/dev/null 2>&1
If exit non-zero: stop. Print:
pulse: wrapper(s) not found — needs scripts/agent-listeners-fleet.sh + scripts/agent-chat-arc-recent.sh.
Ensure you're in the TermLink project root (cd /opt/termlink).
Step 2: Parse arguments
$ARGUMENTS is the operator's tail. Normalize:
- Empty → defaults (limit=5, since=24, human format)
- First positive integer →
--limit Nfor the recent-chat wrapper - Second positive integer →
--since Nfor the recent-chat wrapper --json(anywhere) → emit merged JSON envelope; pass through
The /peers half doesn't take a limit/since — the LIVE filter is implicit and always shows current state.
Step 3: Run both wrappers in parallel
Execute concurrently via Bash:
{
bash scripts/agent-listeners-fleet.sh --json > /tmp/pulse.peers.$$ 2>/dev/null &
PEERS_PID=$!
bash scripts/agent-chat-arc-recent.sh --json --limit "$LIMIT" --since "$SINCE" --exclude-heartbeats > /tmp/pulse.recent.$$ 2>/dev/null &
RECENT_PID=$!
wait "$PEERS_PID" "$RECENT_PID"
}
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.
- 1mo ago First seen · 210 lines · 0 tokens per session scan A 662b05af4529
pulse is a command published in the GitHub repository DimitriGeelen/agentic-engineering-framework (18 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,669 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.
usually
Prompt Pocket — list your high-frequency prompts and pick one to run; manage your go-to prompts with add/delete/edit/find. Generates a native slash dropdown so you can pick a saved prompt directly.
compatibility-audit
Audit all agents for Trinity compatibility by requesting self-diagnostics from each agent.
dashboard-session-list
List all pi sessions (id, status, name, cwd). Runs locally, no LLM.
nio
Nio — scan code, evaluate an action, read the audit report, manage config.