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/shiptoday/forge-plugin-codex/forge-autopilotnpx skills add ShipToday/forge-plugin-codex --skill forge-autopilotgit clone --depth 1 https://github.com/ShipToday/forge-plugin-codexWrote 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/shiptoday/forge-plugin-codex/forge-autopilot)<a href="https://agentmods.dev/skills/shiptoday/forge-plugin-codex/forge-autopilot"><img src="https://agentmods.dev/badge/skills/shiptoday/forge-plugin-codex/forge-autopilot.svg" alt="Measured on agentmods" 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 | $0.00257 | $0.06549 |
| Opus 5 | $0.00129 | $0.03275 |
| Sonnet 5 | $0.00051 | $0.01310 |
| Haiku 4.5 | $0.00026 | $0.00655 |
Grade A, and why
forge-autopilot 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 4d 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 — 561 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge Autopilot
You are routing product development requests to Forge via the forge MCP
server. The user does NOT need to say "forge" or "@forge" — detect their intent
from the skill description above and call the right tool automatically.
Forge's workflow catalog lives on the server side and is fully data-driven.
You don't need to know which workflows exist — forge__start_workflow will
return a classifier prompt listing all available workflows (Forge defaults
plus any org-specific workflows configured for the current user) when it
needs the client AI to choose. Just call it and follow the instructions.
Step 1: Detect connected tools
Before calling any Forge tool, build the connected_tools array by checking
which MCP tools are available in the current session:
| Connector | Look for these tool names |
|---|---|
| jira | searchJiraIssuesUsingJql, createJiraIssue, updateJiraIssue |
| linear | list_issues, get_issue, create_issue, save_issue |
| github | gh CLI available via shell, or GitHub connector tools |
| slack | slack_send_message, slack_search_users, slack_search_channels |
| confluence | searchConfluenceUsingCql, getConfluencePage |
| notion | notion-search, notion-fetch, notion-create-pages |
| granola | search_meetings, get_meeting_transcript |
| figma | get_design_context, get_screenshot, get_metadata |
| local_code | filesystem/shell access (always include in coding environments) |
Only include connectors you can verify. Always include local_code when you
have filesystem access.
Step 1b: Detect local skills
Build the local_skills array by checking your available skills, slash
commands, or rules. Include every skill relevant to product development
or the software development lifecycle — anything a Forge workflow step
could draw on, such as brainstorming, planning, requirements, estimation,
architecture analysis, code review, debugging, testing, or documentation.
Relevance — not whether the skill is project-specific — is the test: a
general-purpose skill still counts if it supports SDLC work.
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.
- 4d ago First seen · 561 lines · 257 tokens per session scan A c02f6afdabc1
forge-autopilot is a skill published in the GitHub repository ShipToday/forge-plugin-codex (2 stars, last pushed 5d ago), licensed MIT. It adds 257 tokens to every session and 6,549 once invoked, about $0.0013 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
Technical Debt Tracking with PMAT
Tracks and manages technical debt using PMAT (Pragmatic AI Labs MCP Agent Toolkit). Use this skill when: User asks about technical debt, TODO comments, or code quality issues Planning sprint work and need to prioritize debt repayment Conducting code audits or technical debt assessments Tracking debt accumulation…
mindtrain
Configure a private MindTrain instance, query its knowledge catalog, create user-approved training domains and knowledge points from AI dialogue or local reference libraries, and run persistent conversational training through Trainer MCP. Use when the user configures MindTrain, asks what domains or topics exist…
github-todo-triage
Use this skill in this repository when asked to fetch, review, triage, or update todos from GitHub issues and pull requests, especially for xing5/mcp-google-sheets. It defines the local workflow for refreshing GitHub state, reviewing new work, prioritizing next actions, and maintaining the repo todo status ledger.
promote-idea
Promote an Inbox bullet from BACKLOG.md to either a GitHub issue (work commitment) or a briefing (briefings/B-NNNN-.md, research/decision support). Asks which based on whether the work is committed or still needs thinking. Removes the original bullet.
triage
Apply a formal state machine to issues — assign category (bug/enhancement/question/spike) and state (needs-triage → needs-info → ready-for-agent → ready-for-human → wontfix). Issues marked ready-for-agent become inputs to supergraph:plan. Use when processing a backlog, reviewing new issues, or preparing work for…
servicenow-change-management
ITSM change-management operations on the ServiceNow Change API via the servicenow-api MCP server — the full change-request lifecycle: query changes, tasks, schedules, CIs, models and standard-change templates; create/update changes and change-tasks; run risk calculation and conflict checks; approve; and delete. Use…