Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jaroslavsoucek-art/Giovanninpx agentmods add skills/jaroslavsoucek-art/giovanni/pulseWrote 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/jaroslavsoucek-art/giovanni/pulse)<a href="https://agentmods.dev/skills/jaroslavsoucek-art/giovanni/pulse"><img src="https://agentmods.dev/badge/skills/jaroslavsoucek-art/giovanni/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/skills/jaroslavsoucek-art/giovanni/pulse"><img src="https://agentmods.dev/badge/skills/jaroslavsoucek-art/giovanni/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 | $0.00051 | $0.01022 |
| Opus 5.5 | $0.00020 | $0.00409 |
| Sonnet 5.5 | $0.00010 | $0.00204 |
| Haiku 4.5 | $0.00005 | $0.00102 |
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 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/giovanni:pulse
The digest answers "what happened since yesterday". Pulse answers "where does each piece of work actually stand".
Those come apart faster than anyone expects. The digest is an event stream: it is excellent at surprises and blind to silence. A work-block with no messages, no tickets moved and no meetings looks identical in a digest to a work-block that does not exist — and the second-most-common failure in a delivery-shaped domain is discovering that something has been quietly stalled for five weeks, in a channel nobody posts to.
Pulse reads state, not events, and reads it from where the work actually leaves traces — which is usually not the tracker.
Usage
/giovanni:pulse # default — all work-blocks, since last pulse
/giovanni:pulse since=<YYYY-MM-DD> # explicit window
/giovanni:pulse block=<slug> # single work-block
/giovanni:pulse quick # counts and deltas only, no narrative
Argument syntax
| Arg | Type | Default | Meaning |
|---|---|---|---|
since=<date> |
parameterized date | last pulse (from memory/pulse/_state.md) |
Lower bound of the window |
block=<slug> |
parameterized string | all | Restrict to one work-block |
quick |
boolean flag | off | Deltas only — skip per-block narrative |
Work-blocks
A work-block is a unit of work the principal tracks as one thing: a workstream, an epic, a market, a product area. Defined per fork in the pulse config (memory/pulse/_blocks.yaml or equivalent) — slug, owner, where its traces live.
Blocks, not people and not tickets. Tickets are too granular to show a trend; people cut across blocks; and the question being asked is "is this piece of work moving", which is a property of the work.
Sources — code over tracker
Order matters, and it is the opposite of the intuitive one:
- The repository. Commits, merged changes, and which paths they touch. Code is the only source that cannot be optimistic — a merged change is work that exists.
- The tracker. Status transitions in the window, and their absence. A ticket that moved "in progress" three weeks ago and has not moved since is the signal; the board view hides exactly this.
- Documents. New or materially edited specs, decisions, plans.
- Everything else — only as corroboration.
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 · 71 lines · 51 tokens per session scan A 65564f2ebb72
pulse is a skill published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,022 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-17.
Other skills, from other repositories
github-project-management
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning.
V3 Swarm Coordination
15-agent hierarchical mesh coordination for v3 implementation. Orchestrates parallel execution across security, core, and integration domains following 10 ADRs with 14-week timeline.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
track-management
Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.
taskmarket-delegate
Delegate work to the TaskMarket agent-worker market - browse open tasks, create tasks with explicit authorization, and track/submit work, so an agent can outsource instead of burning inference on unreliable or low-confidence work.