A daily report that gathers configured sources, combines their findings, detects changes from earlier information, and produces a brief. It is an event-oriented summary of what happened since the previous run.

Use it for a full daily digest, a single configured source, or an intentional rerun that bypasses the normal four-hour timing guard.

A stream of updates can hide important patterns, changes, or conflicts. This turns multiple source pulls into a consolidated daily view and can also run one source alone for troubleshooting.

digest — Skill for Claude Code by jaroslavsoucek-art/Giovanni

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add jaroslavsoucek-art/Giovanni

Claude Code

/plugin install giovanni

Made for: Claude Code.

Or install giovanni, the plugin that ships this one along with the rest of its 11 skills, 1 command, 9 agents, 4 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jaroslavsoucek-art/giovanni/digest/github.svg)](https://agentmods.dev/skills/jaroslavsoucek-art/giovanni/digest)

Your own site

<a href="https://agentmods.dev/skills/jaroslavsoucek-art/giovanni/digest"><img src="https://agentmods.dev/badge/skills/jaroslavsoucek-art/giovanni/digest/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jaroslavsoucek-art/giovanni/digest"><img src="https://agentmods.dev/badge/skills/jaroslavsoucek-art/giovanni/digest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,981 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00025	$0.01981
Opus 5.5	$0.00010	$0.00792
Sonnet 5.5	$0.00005	$0.00396
Haiku 4.5	$0.00003	$0.00198

Measured today against content hash 55e2bfae2934, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

digest 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.

plugin/skills/digest/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/giovanni:digest

Orchestrate the daily digest per ${CLAUDE_PLUGIN_ROOT}/skills/digest/procedure.md. This command is a thin shell — it sets up pre-flight, parses args, fans out giovanni:source-puller agents in parallel, then hands off to the workflow procedure. The mechanics live in the workflow doc and the agents; this file is the invocation contract.

Usage

/giovanni:digest                            # default — full 12-step procedure
/giovanni:digest --force                    # override 4 h cadence guard
/giovanni:digest --source <name>            # debug mode — run a single source pull only
/giovanni:digest --source <name> --force    # both

Argument syntax

Arg	Type	Default	Meaning
`--force`	boolean flag	off	Skip the 4 h cadence guard (Workflow Step 0.3). Use after correcting a botched run or rerunning intentionally.
`--source <name>`	parameterized	none	Run only the named source pull and render its bullets — bypasses synthesis, drift, briefs, shadow. Debug aid for source config tuning. `<name>` must match an entry in `memory/digest_sources.md`.

Quoted strings supported. --flag=value and --flag value both work.

Pre-flight (binding — STOP on failure)

Before spawning any agent, the orchestrator verifies:

CWD check. Working directory contains both memory/digest_sources.md and ${CLAUDE_PLUGIN_ROOT}/docs/digest.md. Otherwise STOP: ERROR: not in a Giovanni repo (no memory/digest_sources.md). Reinvoke from repo root.
State file readable. memory/digest_state.md exists and parses last_run_timestamp as ISO 8601. If missing or empty:
- First run ever → ASK the principal for a manual seed timestamp (e.g. "start window 7 days ago"). Do NOT default.
- Corrupt / missing field → STOP with a diagnostic line pointing at memory/digest-state.template.md.
Cadence guard. If last_run_timestamp is less than 4 h ago AND --force is not set, STOP: INFO: last digest <Nm> ago — re-running this fast pollutes state. Override with --force.
Source config presence. memory/digest_sources.md parses and lists ≥1 source. Empty config is a setup error, not a "quiet day". STOP: ERROR: memory/digest_sources.md has no configured sources. Seed it per memory/digest-sources.template.md.
Required agent files present. ${CLAUDE_PLUGIN_ROOT}/agents/source-puller.md (parallel pull) and — if Step 9/10 will reach them — profile-bootstrap.md. Missing agent file → STOP with which file is absent.

Read the full file on GitHub · 106 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

procedure.md 39 KB

Changes

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 · 106 lines · 25 tokens per session scan A 55e2bfae2934

Subscribe to this mod's changes

digest is a skill published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 1,981 once invoked, about $0.0001 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.

Research agent-framework agentic-ai ai-agents anthropic chief-of-staff

continuum-tools-mcp

Connect MCP servers (Stdio/SSE/StreamableHTTP) to a Continuum agent, configure tool filtering, set up tool-context capture/injection (e.g. sessionid), and read run artifacts (UI widgets, structured tool data). Invoke when the user asks "connect MCP", "filesystem tool", "remote API tool", "auto-capture sessionid"…

shyftlabs/continuum · 94 tokens

continuum-handoffs

Build agent-to-agent transitions with Continuum's Handoff system — triage routing, history summarization modes (FULL/SUMMARY/RECENTN/HYBRID), cycle detection, depth tracking, return-to-parent. Invoke when the user asks "route customer requests to specialists", "agent that can transfer to another", "summarize history…

shyftlabs/continuum · 98 tokens

continuum-llm-providers

Pick the right LLM provider, configure structured outputs, control context-window compression, and use the LLMClient directly. Provider routing is by model-string prefix; LiteLLM has been removed. Also covers Smart Gateway integration for multi-provider routing. Invoke when the user asks about "switch to Claude"…

shyftlabs/continuum · 105 tokens

continuum-observability

Trace agent runs with Langfuse, decorate functions with @observe, collect latency/token/error metrics, and report errors. Invoke when the user asks about "see what the LLM was prompted with", "Langfuse traces", "track latency", "metrics dashboard", "error reporting", or "instrument my function".

shyftlabs/continuum · 70 tokens

continuum-temporal

Build durable agent workflows with Temporal — sequential/parallel/loop/conditional steps, human-in-the-loop approval gates, custom workflows and activities. Invoke when the user asks "long-running workflow", "approval gate", "human in the loop", "retry on failure", "workflow survives restart", or anything…

shyftlabs/continuum · 68 tokens

continuum-testing

Write tests for Continuum agents — mock LLM and memory clients via the DI Container, use fakeredis for sessions, snapshot agent responses, and run pytest-asyncio. Invoke when the user asks "test my agent", "mock the LLM", "fakeredis", "container injection", "pytest", or wants their CI to validate agent behavior…

shyftlabs/continuum · 80 tokens