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.
npx skills add datacore-one/datacore --skill github-triagegit clone --depth 1 https://github.com/datacore-one/datacoreWrote 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/datacore-one/datacore/github-triage)<a href="https://agentmods.dev/skills/datacore-one/datacore/github-triage"><img src="https://agentmods.dev/badge/skills/datacore-one/datacore/github-triage/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/datacore-one/datacore/github-triage"><img src="https://agentmods.dev/badge/skills/datacore-one/datacore/github-triage.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 | $0.00099 | $0.01462 |
| Opus 5.5 | $0.00040 | $0.00585 |
| Sonnet 5.5 | $0.00020 | $0.00292 |
| Haiku 4.5 | $0.00010 | $0.00146 |
Grade A, and why
github-triage scanned grade A with 1 finding 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 17d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
PATH; do not work around it (no curl or other clients against the GitHub How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub triage
The method is the owner's 2026-09-11 triage prompt, kept verbatim in
reference/triage-prompt-2026-09-11.md. Read it in full and follow it.
This file only adds how the nightly run is scoped, bounded and delivered.
Inputs (given in the run prompt)
SCOPE—publicorenterprise. Never both in one run.public: the relevant repositories under datacore-one, datafund, fairDataSociety, plur-ai and plur9, excludingplur-ai/enterprise.enterprise:plur-ai/enterpriseonly. This run touches nothing public, and its outputs never name a customer ("the customer", "an enterprise deployment").
MODE—incremental(Monday–Saturday) orfull(Sunday).incremental: everything waiting on the owner (review requested, assigned, mentioned and unanswered, his PRs with failing checks or requested changes, decisions only he can make), plus every issue or PR updated in the last 26 hours. Deep-review at most 12 PRs, those waiting on the owner first.full: every open issue and PR in scope, as the reference prompt describes. Deep-review at most 40 PRs, ranked by the prioritisation model.
DATE— the run date (YYYY-MM-DD), used in the output file names.OUT— the output folder inside0-personal/(content/reports/github-triage).OWNER— the owner's GitHub login. "Me", "my PRs" and "waiting on me" in the reference prompt all mean this login.
Identity
The owner is OWNER from the run prompt. On the nightshift host gh is logged
in as the bot account (gh api user returns the bot), so never use the
authenticated account as the owner. The reference prompt's "determine my
GitHub identity" step is answered by OWNER. If OWNER is missing, stop and
write that into the report instead of guessing.
Hard boundaries
- Read-only on GitHub. No merge, close, comment, review, label, assign,
issue creation or push. The runner puts a read-only
ghshim first on PATH; do not work around it (no curl or other clients against the GitHub API). - The only files you write are the two outputs below.
- Do not modify the reference prompt or this skill.
- Stay within the deep-review cap; say in the report what you did not reach.
What ships with it
8 files 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.
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.
- 17d ago First seen · 108 lines · 99 tokens per session scan A 8d3548f6ffba
github-triage is a skill published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 1,462 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-30.
Other skills, from other repositories
add-github
Add GitHub channel integration via Chat SDK. PR and issue comment threads as conversations.
nav-pilot
Dispatch a Navigator task doc to Pilot as a labeled GitHub issue. Use when user says "dispatch TASK-XX to Pilot", "hand off to Pilot", "send to Pilot", or "queue for Pilot". One-way handoff (Navigator authors the spec, Pilot executes autonomously).
linear-cli
Use when the user wants to list, view, start, create, or update Linear issues from the terminal via schpet/linear-cli, including setup, auth, repo config, and safe read/write boundaries.
linear-slice
Decompose a plan into dependency-ordered Linear issues (tracer-bullet vertical slices) and release them into the autonomous dispatch pipeline.
add-asana
Add Asana project management MCP integration to Deus. Gives host-side Claude Code sessions read/write access to Asana tasks, projects, sections, and tags via @roychri/mcp-server-asana.
prd-os
PRD creation and PRD execution operating system. Use when the founder asks to turn a rough idea into a PRD, run a Codex review on a PRD or issue, decompose an approved PRD into issue specs, or execute an issue with scope enforcement and receipt-based closeout. Not for general product ideation or casual drafting; this…