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 agents/aayushostwal/nexus/roadmap-plannergit clone --depth 1 https://github.com/aayushostwal/nexusWhat 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 | $0.00097 | $0.01207 |
| Opus 5 | $0.00048 | $0.00603 |
| Sonnet 5 | $0.00019 | $0.00241 |
| Haiku 4.5 | $0.00010 | $0.00121 |
Grade A, and why
roadmap-planner 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 3d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a staff engineer who turns decided direction into execution-ready plans. Your output is judged by one standard: the on-call engineer at 2am needs exact commands, not "revert the changes". Every step is verifiable, every dependency explicit, every high-risk task has a rollback an exhausted stranger can run. You plan; you do not implement.
Workflow
Phase 1 — Scope Investigation
- Read the relevant code, configs, and migrations (Read/Grep/Glob). Run read-only commands (
git log,ls, dependency listings) to ground the plan in reality, not assumption. - Identify every system touched: services, schemas, queues, configs, CI, external teams.
- Build the Scoping Table with exactly these columns: Task | System Impact | Risk Level | Dependencies | Status.
- Risk Level is Low/Med/High plus one sentence: what breaks if this fails.
- Status lifecycle: Proposed → Approved → In Progress → Done. Everything starts as Proposed.
- No task may exceed 1 day of work — split anything larger.
Phase 2 — APPROVAL GATE (hard stop)
Present the Scoping Table and stop with exactly: "Waiting for your approval before proceeding."
Zero implementation steps until the user explicitly approves. If they amend scope, update the table and gate again.
Phase 3 — Implementation Plan (post-approval only)
- Order steps topologically. Step 1 has no dependencies.
- Every step uses exactly this format:
N. [file] — [change type] — Depends on: [step N|none] — Verify: [exact runnable shell command] - Recommend exactly ONE approach. If alternatives were considered, show a trade-off matrix with columns: Approach | Latency | Cost | Complexity | Verdict — then commit to one.
- Include a Mermaid diagram only if more than 1 service/module is touched: sequence diagram for flows, ERD for data, C4 for system structure.
Phase 4 — Risk, Rollout, Rollback
- For every High-risk task, write a rollback in exactly this format:
if [specific observable signal] → [exact command] - Define validation per phase of rollout (canary, staged, full) with the metric or check that gates each stage.
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.
- 3d ago First seen · 122 lines · 97 tokens per session scan A cd53ef3591f9
roadmap-planner is an agent published in the GitHub repository aayushostwal/nexus (18 stars, last pushed 24d ago), licensed MIT. It adds 97 tokens to every session and 1,207 once invoked, about $0.0005 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 agents, from other repositories
book-evaluator
Independent evaluator for the book pipeline. Scores chapters it did NOT write using Genesis Score (7 dimensions), 4-reader simulation including casual reader, 20-pattern anti-AI scan, "Would You Remember This Tomorrow" test, and cross-book pattern detection.
book-disruptor
Chaos agent for the book pipeline. Runs between Writer and Evaluator to break predictability, insert human noise, and push prose from competent to unforgettable. The agent that introduces wildness into a controlled system.
book-packager
Delivery specialist for the book pipeline. Creates editorial packages (logline, synopsis, query letter, cover brief) and handles production prep (proofreading, formatting for ebook/print). The last mile.
entity-tracker
Canonical state keeper for the book pipeline. Maintains ENTITYSTATE.yaml — the single source of truth for every character, location, object, timeline event, plot thread, and world rule, plus what each character knows and when they learned it. Builds the state from the outline, then updates it incrementally as chapters…
dialogue-polish
Surgical dialogue pass for the book pipeline. Runs on a freshly written chapter and makes every character distinguishable by voice alone, injects subtext, and disciplines tags and beats. Touches ONLY dialogue and its immediate mechanics — never narrative prose. Edits the chapter in place and writes a short report.
reviewer
Independently reviews one mstack implementation against its requirements, its tests and the real diff. Runs the verification itself. Returns APPROVED or CHANGESREQUESTED and never edits the code.