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/v-songbird/foreman/roadmapnpx skills add V-Songbird/foreman --skill roadmapgit clone --depth 1 https://github.com/V-Songbird/foremanWrote 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/v-songbird/foreman/roadmap)<a href="https://agentmods.dev/skills/v-songbird/foreman/roadmap"><img src="https://agentmods.dev/badge/skills/v-songbird/foreman/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 | $0.00074 | $0.01126 |
| Opus 5 | $0.00037 | $0.00563 |
| Sonnet 5 | $0.00015 | $0.00225 |
| Haiku 4.5 | $0.00007 | $0.00113 |
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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
foreman:roadmap — pick, add to, correct, review, or check the project roadmap
All reads/writes to ROADMAP.jsonl at the project root go through
${CLAUDE_PLUGIN_ROOT}/scripts/roadmap.js — never Read/Edit the file
directly, the script enforces id computation and parse-before/after-write
mechanically — run it with --help for the command shapes. Read the
Fields section of ${CLAUDE_PLUGIN_ROOT}/roadmap-schema.md if you need
field semantics beyond what's obvious from the names.
Pre-check: if ROADMAP.jsonl doesn't exist at the project root, tell
the user to run /foreman:init first and stop here.
Call 1 — menu
Q1 — "What do you need?" Options:
Pick the next task— read the roadmap, reason about what to work on next, craft a handoff prompt for it.Add a task— append a new entry to the roadmap.Correct a task— fix a stale title, why, what, kind, or planned files on an entry that already exists.Review status— read-only summary of where every task stands.
AskUserQuestion takes four options at most, so the structural doctor is
reached by asking for it rather than from this menu — the routing just
below carries the phrasings that get there.
If args were provided and read like a task description rather than a question, treat it as a seed for "Add a task" and skip this call. If they read like a pick request or a hint about what to pick ("what's next on auth", "something quick I can finish today"), go straight to "Pick the next task" with the hint in hand — that branch says what to do with it. If they name an entry that already exists and say what's wrong with it ("003's what is out of date", "retarget 007 at the proxy"), that's "Correct a task". If they say the roadmap itself looks broken ("my roadmap is broken", "is the roadmap file healthy"), go straight to "Check the roadmap".
If they ask to clear out or archive finished work ("archive the finished
tasks", "get the done ones out of the way"), skip the menu: run list --status done,dropped,rejected --summary, show those ids, and ask one
AskUserQuestion (Archive them / Leave them). On yes, echo '{"ids":["001","002"]}' | node ${CLAUDE_PLUGIN_ROOT}/scripts/roadmap.js archive — one call, all the ids, nothing else moves. restore with the
same shape is the way back if one has to change again.
What ships with it
6 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 · 104 lines · 74 tokens per session scan A a26316c02326
roadmap is a skill published in the GitHub repository V-Songbird/foreman (34 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 1,126 once invoked, about $0.0004 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
compress
Prompt-Studio memory compressor. Shrinks CLAUDE.md, todo lists, and preference files into Prompt-Studio's lean format to cut input tokens on every load. Preserves all technical substance, code, URLs, and structure. Compressed output overwrites the original; human-readable backup stored out-of-tree as FILE.original.md…
lean-commit
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes…
lean-gain
Show Lean's measured impact as a compact scoreboard: less code, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger: /lean-gain, "lean gain", "what does lean save", "show lean impact", "lean scoreboard".
fellowship
Multi-task orchestrator. Coordinates agent teammates (led by Gandalf) running /quest (code) or /scout (research) workflows. Use when you have multiple independent tasks to run in parallel.
quest
Use for any non-trivial task. Orchestrates the Research-Plan-Implement cycle with compaction between phases, integrating council, lembas, gather-lore, and warden. Enforces discipline and phase gates.
optimize-claude-opus-5-prompts
Clarify, audit, and rewrite rough or existing prompts for Claude Opus 5 using Anthropic's official prompting guidance. Use when a user asks to optimize, improve, migrate, debug, or design a prompt, system prompt, or agent harness for Claude Opus 5 (claude-opus-5), including requests phrased as Opus 5 prompt…