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/tqnonline/agent-forge/backlog-githubnpx skills add tqnonline/agent-forge --skill backlog-githubgit clone --depth 1 https://github.com/tqnonline/agent-forgeWhat 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 | $0.00149 | $0.01049 |
| Opus 5 | $0.00075 | $0.00524 |
| Sonnet 5 | $0.00030 | $0.00210 |
| Haiku 4.5 | $0.00015 | $0.00105 |
Grade A, and why
backlog-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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Issues Backlog Exporter
Version: 1.0 | Role: GitHub Issues Creation Specialist Methodology: Gather Context > Cross-Reference > Create Issues > Verify
You take platform-neutral backlog files produced by backlog-decompose and create issues directly in GitHub via the GitHub MCP server.
MCP tools used (available via GitHub MCP server, not listed in allowed-tools):
list_issues, search_issues, list_issue_types, issue_write, sub_issue_write
Prerequisites
- Platform-neutral backlog must exist at
{project}/specs/backlog/{epic-name}-backlog.md - If no backlog file exists, invoke
/backlog-decomposefirst - GitHub MCP server must be connected
Phase 1: Gather GitHub Context
Use AskUserQuestion to collect:
| Field | Required | Example |
|---|---|---|
| Repository owner/name | Yes | acme-corp/platform-api |
| Milestone | No | v2.1 |
Phase 2: Cross-Reference
Avoid creating duplicate issues:
- Call
list_issuesfor the target repository to retrieve open issues - Compare generated backlog titles against existing issues using fuzzy matching
- Flag potential duplicates -- ask user: skip, update existing, or create new
- Call
list_issue_typesto verify available issue types for the repository - Confirm label and milestone availability; note any that need manual creation
Phase 3: Create Issues
Map backlog items to GitHub issue fields:
| Backlog Field | GitHub Field |
|---|---|
| Title | Title |
| Description + AC | Body (Markdown with acceptance criteria) |
| Work item type | Label (e.g., epic, feature, user-story, risk) |
| Priority (1/2/3) | Label (e.g., priority:must, priority:should, priority:could) |
| Story points | Label (e.g., points:5) or body metadata |
| Milestone | Milestone |
| Work item type | Issue Type (if available) |
Execute in order:
issue_writefor all parent-level items (epics, then features) -- capture returned issue numbersissue_writefor all child items (stories, technical stories, risks, impediments, CI items)sub_issue_writeto establish parent-child hierarchy using captured issue numberssearch_issuesto verify all items were created successfully
What ships with it
3 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.
- yesterday First seen · 99 lines · 149 tokens per session scan A fd85d7a876af
backlog-github is a skill published in the GitHub repository tqnonline/agent-forge (2 stars, last pushed 3mo ago), licensed BSD-3-Clause. It adds 149 tokens to every session and 1,049 once invoked, about $0.0007 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
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
setup-matt-pocock-skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.