triage-github

triage-github is a command for Claude Code from datacore-one/datacore. It costs 10 tokens per session (829 once invoked), scanned A, original, MIT.

A command that checks GitHub repositories for recent activity, summarises the results, and turns actionable findings into GTD tasks. GTD, or Getting Things Done, is a method for organising tasks by deciding what action each item needs.

In plain words
What is it for?
Use it to discover repositories, scan the last 24 hours of activity, create tasks, and write a Markdown summary.
Why use it?
It replaces manually checking several repositories and copying follow-up work into a task list.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .datacore/modules/github/lib/repo_discovery.py \.

Good fit Use it to discover repositories, scan the last 24 hours of activity, create tasks, and write a Markdown summary.

Compare 6 commands from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore
agentmods
npx agentmods add commands/datacore-one/datacore/triage-github

Made for: Claude Code.

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 triage-github

README.md
[![agentmods](https://agentmods.dev/badge/commands/datacore-one/datacore/triage-github/github.svg)](https://agentmods.dev/commands/datacore-one/datacore/triage-github)
Your own site
<a href="https://agentmods.dev/commands/datacore-one/datacore/triage-github"><img src="https://agentmods.dev/badge/commands/datacore-one/datacore/triage-github/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 triage-github

Your own site · 80×15
<a href="https://agentmods.dev/commands/datacore-one/datacore/triage-github"><img src="https://agentmods.dev/badge/commands/datacore-one/datacore/triage-github.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 829 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 $0.00010 $0.00829
Opus 5.5 $0.00004 $0.00332
Sonnet 5.5 $0.00002 $0.00166
Haiku 4.5 $0.00001 $0.00083

Measured yesterday against content hash ce87956ec240, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

triage-github 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 yesterday.

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.

.datacore/modules/github/commands/triage-github.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/triage-github

Scan GitHub repos for activity, generate a summary, and create actionable GTD tasks.

Trigger

  • Standalone: /triage-github
  • Called by /today hook
  • Can be triggered by nightshift as a pre-processing step

Behavior

Execute these steps in order:

Step 1: Discover Repos

Run repo discovery (uses cache if < 7 days old):

python3 .datacore/modules/github/lib/repo_discovery.py \
  --data-dir ~/Data

Parse the JSON output to get the list of orgs and the org_to_spaces mapping.

Step 2: Scan GitHub

Run the full scan using discovered orgs:

python3 .datacore/modules/github/lib/github_scanner.py \
  --username <username from module settings> \
  --orgs "<comma-separated orgs from step 1>" \
  --hours 24 \
  --cache 0-personal/.datacore/module-data/github/data/scan_cache.json \
  --format json

Step 3: Create Tasks

If auto_task_create is enabled (default: true), create tasks from actionable items:

python3 .datacore/modules/github/lib/task_creator.py \
  --scan-file 0-personal/.datacore/module-data/github/data/scan_cache.json \
  --repos-file 0-personal/.datacore/module-data/github/data/repos.json \
  --data-dir ~/Data

Step 4: Generate Summary

Use the scan results to produce a markdown summary. Call format_summary() from github_scanner.py or generate inline using this template:

YOUR ITEMS section (full structured detail for mentions + authored issues):

### GitHub: Your Items

**@<username> mentions:**
- owner/repo#N — "Issue title"
  State: open | [View](url)

**Your issues with new activity:**
- owner/repo#N — "Issue title"
  Latest by @commenter: comment snippet...
  [View](url)

OTHER ACTIVITY section (compact counts per org):

### GitHub: Org Activity

| Org | New Issues | Closed | PRs Merged |
|-----|-----------|--------|------------|
| org-name (space) | N | N | N |

TASKS CREATED section (audit trail):

### GitHub: Tasks Created

- N new tasks created in next_actions.org
- N items skipped (already tracked)
- Tasks tagged :AI:github: for nightshift processing

Read the full file on GitHub · 126 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. yesterday Changed ce87956ec240
  2. 20d ago Changed 2d28f2c72493
  3. 1mo ago First seen · 126 lines · 10 tokens per session scan A 33ef9c11869f

Subscribe to this mod's changes

triage-github is a command published in the GitHub repository datacore-one/datacore (4 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 829 once invoked, about $0.0000 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 2026-09-03.