syndicate-run

syndicate-run is a skill for Claude Code from aadarshvelu/syndicate. It costs 44 tokens per session (1,041 once invoked), scanned A, original, MIT.

A command that runs the full syndicate news pipeline: collecting items from Gmail, RSS feeds, and Twitter, linking and removing duplicates, creating summaries, exporting results, and sending notifications.

In plain words
What is it for?
Use it to process a backlog of incoming news, optionally skip selected sources or export steps, limit the number of summaries, and publish the resulting archive.
Why use it?
It combines the repeated processing steps into one run and checks required settings before starting a long operation.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the syndicate-pipeline plugin — 11 skills shipped together

Good fit Use it to process a backlog of incoming news, optionally skip selected sources or export steps, limit the number of summaries, and publish the resulting archive.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aadarshvelu/syndicate/syndicate-run
Install

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.

Any agent
npx skills add aadarshvelu/syndicate --skill syndicate-run
Clone the repo
git clone --depth 1 https://github.com/aadarshvelu/syndicate

Made for: Claude Code.

Or install syndicate-pipeline, the plugin that ships this one along with the rest of its 11 skills.

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.

agentmods badge for syndicate-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/aadarshvelu/syndicate/syndicate-run/github.svg)](https://agentmods.dev/skills/aadarshvelu/syndicate/syndicate-run)
Your own site
<a href="https://agentmods.dev/skills/aadarshvelu/syndicate/syndicate-run"><img src="https://agentmods.dev/badge/skills/aadarshvelu/syndicate/syndicate-run/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.

agentmods 80×15 button for syndicate-run

Your own site · 80×15
<a href="https://agentmods.dev/skills/aadarshvelu/syndicate/syndicate-run"><img src="https://agentmods.dev/badge/skills/aadarshvelu/syndicate/syndicate-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,041 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.01041
Opus 5 $0.00022 $0.00521
Sonnet 5 $0.00009 $0.00208
Haiku 4.5 $0.00004 $0.00104

Measured 8d ago against content hash fb09497886f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

syndicate-run 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 8d 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.

skills/syndicate-run/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/syndicate-run

You are running the full syndicate pipeline. Long-running (typically 30–90 min depending on backlog and AI provider) and writes to the DB plus pushes to the news-archive git remote. Only run when the user explicitly asked.

This is the on-demand equivalent of the user's scheduled cron. It does not schedule the next wake-up — scheduling is the user's local concern (launchd / systemd / cron / etc.) and is documented in the README.

Step 1 — preflight

Run status once before kicking off:

cd "${SYNDICATE_REPO:-$(pwd)}" && uv run python -m pipeline.cli status

Report items_unsummarized and the current last_run_per_channel.<ch>.ok flags. If any required env var (per the /syndicate-heal recommended-vars list) is missing, stop and report — the run will fail mid-flight otherwise.

Step 2 — run

Parse $ARGUMENTS for skip flags and --summarize-limit N:

cd "${SYNDICATE_REPO:-$(pwd)}" && uv run python -m pipeline.cli run \
    ${skip_gmail:+--skip-gmail} \
    ${skip_rss:+--skip-rss} \
    ${skip_twitter:+--skip-twitter} \
    ${skip_git:+--skip-git} \
    --summarize-limit ${summarize_limit:-50}

The output envelope contains a full OrchestratorResult dict:

{
  "ok": true,
  "result": {
    "started_at": "...",
    "finished_at": "...",
    "ok": true,
    "gmail":     {"ok": true, "fetched": N, "saved": N, ...},
    "rss":       {...},
    "twitter":   {...},
    "relation":  {...},
    "dedup":     {...},
    "summarize": {...},
    "git":       {"ok": true, "exported_today": N, "committed": true, "pushed": true, ...},
    "errors": []
  },
  "log_path": "logs/<date>.txt"
}

By default the run also posts a summary to Telegram (matches uv run syndicate behavior). Pass --no-notify if the user wants to skip that.

Step 3 — report

Render the standard box summary that the user is familiar with from the launchd run output and from Telegram:

════════════════════════════════════════════════════════════════════
  SYNDICATE  ·  <finished_at>  ·  <duration>  ·  <OK|FAILED>
════════════════════════════════════════════════════════════════════
  ✓  Gmail         fetched=N saved=N skipped=N failed=N
  ✓  RSS           fetched=N saved=N skipped=N failed=N
  ✓  Twitter       fetched=N saved=N skipped=N failed=N
  ✓  Relation      examined=N standalone=N reactions=N
  ✓  Dedup         examined=N clusters=N demoted=N [method=N ...]
  ✓  Summarize     examined=N done=N skipped=N
  ✓  Git           today=+N yesterday=+N · committed · pushed
════════════════════════════════════════════════════════════════════

Read the full file on GitHub · 110 lines

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.

  1. 8d ago First seen · 110 lines · 44 tokens per session scan A fb09497886f0

Subscribe to this mod's changes

syndicate-run is a skill published in the GitHub repository aadarshvelu/syndicate (2 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 1,041 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

provider-integration

Adds new AI providers to claude-council, configures provider API settings, troubleshoots provider connections, and documents the provider script interface. Covers creating provider shell scripts, setting API keys, and validating connectivity. Triggers on "add provider", "new AI agent", "provider not working", "API…

hex/claude-council · 74 tokens

update-lid

Configure or reconcile a project for linked-intent development (LID). Dispatches on project state — fresh bootstrap, append directives to an existing agent-instructions file (AGENTS.md or CLAUDE.md), add missing mode marker, reconcile convention drift, or run mode transitions. Invoked as /update-lid. For fresh…

jszmajda/lid · 105 tokens

map-codebase

Bootstrap LID in an existing (brownfield) codebase. Deep-reads every file in the declared scope, offers lens-based clustering options, generates skeleton LLDs/HLD/EARS bottom-up, then creates arrow docs and prompts the user to flesh out the skeletons. Token-intensive by design. Use when asked to map a codebase…

jszmajda/lid · 92 tokens

superbrain-distill

Internal SuperBrain skill — run by the detached capture child to distill a session-event delta into routed Obsidian notes. Not for direct user invocation.

m3talux/superbrain · 36 tokens

design

Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…

cryndoc/polisade-orchestrator · 162 tokens

recursive-decomposition

Handle tasks that exceed the context window by decomposing them: size and filter the input, chunk it, run recursive sub-agents on independent parts, verify on small windows, and synthesise programmatically, following the Recursive Language Models (RLM) research by Zhang, Kraska and Khattab (2025). Use when a task…

massimodeluisa/recursive-decomposition-skill · 151 tokens