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 agentmods add skills/oortonaut/task-graph-mcp/github-linkingnpx skills add Oortonaut/task-graph-mcp --skill github-linkinggit clone --depth 1 https://github.com/Oortonaut/task-graph-mcpWhat 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 | $0.00030 | $0.01912 |
| Opus 5 | $0.00015 | $0.00956 |
| Sonnet 5 | $0.00006 | $0.00382 |
| Haiku 4.5 | $0.00003 | $0.00191 |
Grade A, and why
github-linking 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub ↔ Task Graph Linking
Conventions and processes for maintaining bidirectional traceability between GitHub issues/PRs and task-graph tasks.
Prerequisite: Understand task-graph-basics for tool reference.
Overview
GitHub Task Graph
┌──────────────┐ attach ┌──────────────┐
│ Issue #42 │◄──────────────►│ brave-fox │
│ (bug report)│ github/issue │ (work task) │
└──────────────┘ └──────────────┘
│ │
│ PR #99 "Fixes #42" │ attach github/pr
▼ ▼
┌──────────────┐ attach ┌──────────────┐
│ PR #99 │◄──────────────►│ brave-fox │
│ (fix) │ github/pr │ (same task) │
└──────────────┘ └──────────────┘
Key idea: GitHub is the external record of truth. Task-graph is the internal coordination layer. Attachments bridge them.
Configuration
The project config (task-graph/config.yaml) defines these integration primitives:
Attachment Types
| Type | MIME | Mode | Purpose |
|---|---|---|---|
github/issue |
application/json |
replace | Link to a GitHub issue |
github/pr |
application/json |
replace | Link to a GitHub PR |
github/comment |
text/plain |
append | Notable comments from GitHub |
Dependency Type
| Type | Display | Blocks | Purpose |
|---|---|---|---|
tracks |
horizontal | none | Informational cross-reference to an external item |
Tags
| Tag | Category | Purpose |
|---|---|---|
github |
integration | Mark a task as linked to GitHub |
bug |
type | Mirror GitHub "bug" label |
enhancement |
type | Mirror GitHub "enhancement" label |
Process 1: Link Existing Issue to New Task
When a GitHub issue exists and you want to track work in task-graph:
# 1. Create the task
create(
title="Fix list_tasks ID truncation",
description="list_tasks truncates petname IDs to 8 chars in markdown output, making them unusable",
tags=["github", "bug"]
)
→ task_id (e.g. "brave-fox")
# 2. Attach the GitHub issue reference
attach(
agent=worker_id,
task="brave-fox",
type="github/issue",
content='{"repo": "Oortonaut/task-graph-mcp", "number": 1, "url": "https://github.com/Oortonaut/task-graph-mcp/issues/1"}'
)
# 3. (Optional) Add a comment on the GitHub issue pointing back
# gh issue comment 1 --body "Tracked in task-graph: brave-fox"
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.
- 2d ago First seen · 286 lines · 30 tokens per session scan A 503e3c141b83
github-linking is a skill published in the GitHub repository Oortonaut/task-graph-mcp (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,912 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.
Other skills, from other repositories
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
teamharness-task-delegation
Use when a Leader turns ready Quick Task or Project Work state into Worker task instructions, sends assignment messages, checks submitted results, and defines completion/blocker report contracts. Do not use to create projects, create rooms, or execute Worker tasks.
github-workflow
Use GitHub workflow tools to read work status, draft reports, summarize follow-ups, and execute only approved issue mutations.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.