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/dirien/yet-another-agent-harness/roadmapnpx skills add dirien/yet-another-agent-harness --skill roadmapgit clone --depth 1 https://github.com/dirien/yet-another-agent-harnessWrote 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/dirien/yet-another-agent-harness/roadmap)<a href="https://agentmods.dev/skills/dirien/yet-another-agent-harness/roadmap"><img src="https://agentmods.dev/badge/skills/dirien/yet-another-agent-harness/roadmap.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 | $0.00060 | $0.01588 |
| Opus 5 | $0.00030 | $0.00794 |
| Sonnet 5 | $0.00012 | $0.00318 |
| Haiku 4.5 | $0.00006 | $0.00159 |
Grade A, and why
roadmap 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 5d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strategic Roadmap Management
Manage project roadmaps through five modes: sync ROADMAP.md with GitHub reality, bootstrap planning files from scratch, brainstorm new features collaboratively, get a quick status summary, or show help.
Prerequisite check
gh --version 2>/dev/null && gh auth status 2>/dev/null
If gh is not installed, direct the user to
https://cli.github.com. If not authenticated, direct them to run
gh auth login. Do not proceed without a working, authenticated
GitHub CLI.
Constitutional principle
CONTEXT.md is the project constitution. All modes must read and respect the boundaries defined in CONTEXT.md. If CONTEXT.md exists, read it first and constrain all analysis and recommendations.
When any recommendation would violate CONTEXT.md boundaries:
- Explicitly flag the violation
- Explain which boundary would be crossed
- Suggest an alternative that respects the boundaries
Mode dispatch
Determine the mode from the user's input. If no mode is specified, default to sync.
| Argument | Mode | Purpose |
|---|---|---|
| (none) | sync | Sync ROADMAP.md with GitHub, recommend priorities |
sync |
sync | Same as default |
generate |
generate | Bootstrap CONTEXT.md + ROADMAP.md from scratch |
brainstorm |
brainstorm | Creative ideation session (read-only) |
status |
status | Quick read-only summary |
help |
help | Show available modes |
Mode: sync
Synchronize ROADMAP.md with GitHub and provide prioritized recommendations. This is the primary mode.
- Fetch open issues, recently closed issues, and milestones via
ghCLI - Read ROADMAP.md and CONTEXT.md
- Check for legacy section layout — if found, ask the user whether to migrate to canonical structure (Vision → Immediate Focus → Near-Term → Future → Completed → Boundaries)
- Detect discrepancies between ROADMAP.md and GitHub (issues marked done but still open, open but closed, missing entirely)
- Update ROADMAP.md — fix discrepancies, move closed issues to "Completed Milestones" under quarterly sub-headings
- Estimate LOE for open issues without
effort/*labels using the heuristics inreferences/label-config.md - Sync GitHub labels — create missing labels, add/remove
roadmap/*labels to match ROADMAP.md sections - Append LOE indicators (
[S],[M],[L]) to issue lines in ROADMAP.md - Generate 3-5 prioritized recommendations based on dependencies, impact vs effort, theme coherence, and LOE balance
- Present summary of all changes and recommendations
What ships with it
5 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.
- 5d ago First seen · 186 lines · 60 tokens per session scan A f39c11314a91
roadmap is a skill published in the GitHub repository dirien/yet-another-agent-harness (20 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 1,588 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
subagent-delegation
Canonical protocol for delegating GSD work to native Antigravity subagents — when to delegate, how to invoke, workspace isolation modes, and the inline fallback for older IDE versions.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
project-init
Scaffold an unconfigured directory into a configured pi project. Interactive, profile-driven: previews the planned writes, then writes AGENTS.md, .pi/settings.json and prompt files — optionally also a knowledge base, an openspec/ scaffold, and user-global /.pi/agent/settings.json. Use on a bare directory, or when the…